Solving complex tasks in a single attempt is challenging for large language models (LLMs). Iterative interaction with the environment and feedback is often required to achieve success, making effective feedback utilization a critical topic. Existing approaches either struggle with length generalization or rely on naive retries without leveraging prior information. In this paper, we introduce FTTT, a novel paradigm that formulates feedback utilization as an optimization problem at test time. Additionally, we propose a learnable test-time optimizer, OpTune, to effectively exploit feedback. Experiments on two LLMs across four reasoning datasets demonstrate that FTTT and OpTune achieve superior scalability and performance.

The significant breakthroughs of Medical Multi-Modal Large Language Models (Med-MLLMs) renovate modern healthcare with robust information synthesis and medical decision support. However, these models are often evaluated on benchmarks that are unsuitable for the Med-MLLMs due to the intricate nature of the real-world diagnostic frameworks, which encompass diverse medical specialties and involve complex clinical decisions. Thus, a clinically representative benchmark is highly desirable for credible Med-MLLMs evaluation. To this end, we introduce Asclepius, a novel Med-MLLM benchmark that comprehensively assesses Med-MLLMs in terms of: distinct medical specialties (cardiovascular, gastroenterology, etc.) and different diagnostic capacities (perception, disease analysis, etc.). Grounded in 3 proposed core principles, Asclepius ensures a comprehensive evaluation by encompassing 15 medical specialties, stratifying into 3 main categories and 8 sub-categories of clinical tasks, and exempting overlap with the existing VQA dataset. We further provide an in-depth analysis of 6 Med-MLLMs and compare them with 3 human specialists, providing insights into their competencies and limitations in various medical contexts. Our work not only advances the understanding of Med-MLLMs’ capabilities but also sets a precedent for future evaluations and the safe deployment of these models in clinical environments.

Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.

Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models (LLMs) demonstrate promising potential in coding tasks, their performance in debugging remains limited. Current LLM-based methods often focus on isolated steps and struggle with complex bugs. In this paper, we propose the first end-to-end framework, UniDebugger, for unified debugging through multi-agent synergy. It mimics the entire cognitive processes of developers, with each agent specialized as a particular component of this process rather than mirroring the actions of an independent expert as in previous multi-agent systems. Agents are coordinated through a three-level design, following a cognitive model of debugging, allowing adaptive handling of bugs with varying complexities. Experiments on extensive benchmarks demonstrate that UniDebugger significantly outperforms state-of-the-art repair methods, fixing 1.25x to 2.56x bugs on the repo-level benchmark, Defects4J. This performance is achieved without requiring ground-truth root-cause code statements, unlike the baselines. Our source code is available on an anonymous link: https://github.com/BEbillionaireUSD/UniDebugger.

Equipped with the capability to call functions, modern LLM agents can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools relies heavily not just on the advanced capabilities of LLM agents but also on precise user instructions, which often cannot be ensured in the real world. To evaluate the performance of LLM agents tool-use under imperfect instructions, we meticulously examine the real-world instructions queried from users, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We find that due to the next-token prediction training objective, LLM agents tend to arbitrarily generate the missed argument, which may lead to hallucinations and risks. To address this issue, we propose a novel framework, Ask-when-Needed, which prompts LLM agents to ask questions to users whenever they encounter obstacles due to unclear instructions. Moreover, to reduce the manual labor involved in user-LLM interaction and assess LLM agents’ performance in tool utilization from both accuracy and efficiency perspectives, we design an automated evaluation tool named ToolEvaluator. Our experiments demonstrate that the Ask-when-Needed significantly outperforms existing frameworks for tool learning in the Noisy ToolBench. We will release all related code and datasets to support future research.

Recent advances in large language models (LLMs) have shown significant promise, yet their evaluation raises concerns, particularly regarding data contamination due to the lack of access to proprietary training data. To address this issue, we present C²LEVA, a comprehensive bilingual benchmark featuring systematic contamination prevention. C²LEVA firstly offers a holistic evaluation encompassing 22 tasks, each targeting a specific application or ability of LLMs, and secondly a trustworthy assessment due to our contamination-free tasks, ensured by a systematic contamination prevention strategy that fully automates test data renewal and enforces data protection during benchmark data release. Our large-scale evaluation of 15 open-source and proprietary models demonstrates the effectiveness of C²LEVA.

Recent failures such as Google Gemini generating people of color in Nazi-era uniforms illustrate how AI outputs can be factually plausible yet socially harmful. AI models are increasingly evaluated for “fairness,” yet existing benchmarks often conflate two fundamentally different dimensions: factual correctness and normative fairness. A model may generate responses that are factually accurate but socially unfair, or conversely, appear fair while distorting factual reality. We argue that identifying the boundary between fact and fair is essential for meaningful fairness evaluation. We introduce Fact-or-Fair, a benchmark with (i) objective queries aligned with descriptive, fact-based judgments, and (ii) subjective queries aligned with normative, fairness-based judgments. Our queries are constructed from 19 statistics and are grounded in cognitive psychology, drawing on representativeness bias, attribution bias, and ingroup–outgroup bias to explain why models often misalign fact and fairness. Experiments across ten frontier models reveal different levels of fact-fair trade-offs. By reframing fairness evaluation, we provide both a new theoretical lens and a practical benchmark to advance the responsible model assessments. Our test suite is publicly available at https://github.com/uclanlp/Fact-or-Fair.

Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications. Despite this progress, we find that these models struggle with multi-hop reasoning and exhibit decreased performance in the presence of noisy contexts. In this paper, we introduce Reasoning with Attributions, a novel approach that prompts LMs to supply attributions for each assertion during their reasoning. We validate our approach through experiments on three multi-hop datasets, employing both proprietary and open-source models, and demonstrate its efficacy and resilience. Furthermore, we explore methods to augment reasoning capabilities via fine-tuning and offer an attribution-annotated dataset and a specialized training strategy. Our fine-tuned model achieves competitive performance on multi-hop reasoning benchmarks, closely paralleling proprietary LMs such as ChatGPT and Claude-instant.

This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e.g., ChatGPT). LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages. To systematically evaluate the cultural dominance issue, we build a benchmark of concrete (e.g., holidays and songs) and abstract (e.g., values and opinions) cultural objects. Empirical results show that the representative GPT models suffer from the culture dominance problem, where GPT-4 is the most affected while text-davinci-003 suffers the least from this problem. Our study emphasizes the need to critically examine cultural dominance and ethical considerations in their development and deployment. We show that two straightforward methods in model development (i.e., pretraining on more diverse data) and deployment (e.g., culture-aware prompting) can significantly mitigate the cultural dominance issue in LLMs.

We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4. Despite LLMs’ prowess in tasks like writing assistance, code generation, and machine translation, assessing their ability to reason has been challenging. Traditional evaluations often prioritize accuracy on downstream tasks over direct assessments of reasoning processes. LogicAsker addresses this gap by employing a set of atomic reasoning skills grounded in propositional and predicate logic to systematically examine and improve the reasoning prowess of LLMs. Our methodology reveals significant gaps in LLMs’ learning of logical rules, with identified reasoning failures ranging from 29% to 90% across different models. Moreover, we leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5%. To our knowledge, this is the first effort to utilize test case outcomes to effectively refine LLMs’ formal reasoning capabilities. We make our code, data, and results publicly available(https://github.com/yxwan123/LogicAsker) to facilitate further research and replication of our findings.

Recent research has focused on examining Large Language Models’ (LLMs) characteristics from a psychological standpoint, acknowledging the necessity of understanding their behavioral characteristics. The administration of personality tests to LLMs has emerged as a noteworthy area in this context. However, the suitability of employing psychological scales, initially devised for humans, on LLMs is a matter of ongoing debate. Our study aims to determine the reliability of applying personality assessments to LLMs, explicitly investigating whether LLMs demonstrate consistent personality traits. Analysis of 2,500 settings per model, including GPT-3.5, GPT-4, Gemini-Pro, and LLaMA-3.1, reveals that various LLMs show consistency in responses to the Big Five Inventory, indicating a satisfactory level of reliability. Furthermore, our research explores the potential of GPT-3.5 to emulate diverse personalities and represent various groups—a capability increasingly sought after in social sciences for substituting human participants with LLMs to reduce costs. Our findings reveal that LLMs have the potential to represent different personalities with specific prompt instructions.

Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often lack access to world knowledge critical for visual reasoning. In this work, we propose Visual Table, a novel form of visual representation tailored for visual reasoning. Visual tables are constructed as hierarchical descriptions of visual scenes, featuring a scene description and multiple object-centric descriptions covering categories, attributes, and knowledge. Thanks to the structural and textual formats, visual tables offer unique properties over mere visual embeddings, such as explainability and controllable editing. Furthermore, they deliver instance-level world knowledge and detailed attributes that are essential for visual reasoning. To create visual tables, we develop a generator trained on the dataset with collected, small-scale annotations. Extensive results on 11 visual reasoning benchmarks demonstrate that the generated visual tables significantly outperform previous structural and text-based representations. Moreover, they consistently enhance state-of-the-art multi-modal large language models across diverse benchmarks, showcasing their potential for advancing visual reasoning tasks. Our code is available at https://github.com/LaVi-Lab/Visual-Table.

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice. XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We utilize XSafety to empirically study the multilingual safety for 4 widely-used LLMs, including both close-API and open-source models. Experimental results show that all LLMs produce significantly more unsafe responses for non-English queries than English ones, indicating the necessity of developing safety alignment for non-English languages. In addition, we propose a simple and effective prompting method to improve the multilingual safety of ChatGPT by enhancing cross-lingual generalization of safety alignment. Our prompting method can significantly reduce the ratio of unsafe responses by 42% for non-English queries. We will release all the data and results to facilitate future research on LLMs’ safety.

Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding. To address this gap, we propose a Time Gating Video LLM (TG-Vid) designed to enhance temporal modeling through a novel Time Gating module (TG). The TG module employs a time gating mechanism on its sub-modules, comprising gating spatial attention, gating temporal attention, and gating MLP. This architecture enables our model to achieve a robust understanding of temporal information within videos. Extensive evaluation of temporal-sensitive video benchmarks (i.e., MVBench, TempCompass, and NExT-QA) demonstrates that our TG-Vid model significantly outperforms the existing Video LLMs. Further, comprehensive ablation studies validate that the performance gains are attributed to the designs of our TG module. Our code is available at https://github.com/LaVi-Lab/TG-Vid.

With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model’s capabilities has become an increasingly significant issue. The absence of a comprehensive Chinese benchmark that thoroughly assesses a model’s performance, the unstandardized and incomparable prompting procedure, and the prevalent risk of contamination pose major challenges in the current evaluation of Chinese LLMs. We present CLEVA, a user-friendly platform crafted to holistically evaluate Chinese LLMs. Our platform employs a standardized workflow to assess LLMs’ performance across various dimensions, regularly updating a competitive leaderboard. To alleviate contamination, CLEVA curates a significant proportion of new data and develops a sampling strategy that guarantees a unique subset for each leaderboard round. Empowered by an easy-to-use interface that requires just a few mouse clicks and a model API, users can conduct a thorough evaluation with minimal coding. Large-scale experiments featuring 23 Chinese LLMs have validated CLEVA’s efficacy.

Code search is to search reusable code snippets from source code corpus based on natural languages queries. Deep learning-based methods on code search have shown promising results. However, previous methods focus on retrieval accuracy, but lacked attention to the efficiency of the retrieval process. We propose a novel method CoSHC to accelerate code search with deep hashing and code classification, aiming to perform efficient code search without sacrificing too much accuracy. To evaluate the effectiveness of CoSHC, we apply our methodon five code search models. Extensive experimental results indicate that compared with previous code search baselines, CoSHC can save more than 90% of retrieval time meanwhile preserving at least 99% of retrieval accuracy.

In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation (NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the discrepancies between Seq2Seq pretraining and NMT finetuning limit the translation quality (i.e., domain discrepancy) and induce the over-estimation issue (i.e., objective discrepancy). Based on these observations, we further propose simple and effective strategies, named in-domain pretraining and input adaptation to remedy the domain and objective discrepancies, respectively. Experimental results on several language pairs show that our approach can consistently improve both translation performance and model robustness upon Seq2Seq pretraining.

Despite recent progress in open-domain dialogue evaluation, how to develop automatic metrics remains an open problem. We explore the potential of dialogue evaluation featuring dialog act information, which was hardly explicitly modeled in previous methods. However, defined at the utterance level in general, dialog act is of coarse granularity, as an utterance can contain multiple segments possessing different functions. Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it. To utilize segment act flows, sequences of segment acts, for evaluation, we develop the first consensus-based dialogue evaluation framework, FlowEval. This framework provides a reference-free approach for dialog evaluation by finding pseudo-references. Extensive experiments against strong baselines on three benchmark datasets demonstrate the effectiveness and other desirable characteristics of our FlowEval, pointing out a potential path for better dialogue evaluation.

Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage these large models as knowledge bases for downstream tasks. In this work, we answer the aforementioned question in unsupervised knowledge-grounded conversation. We explore various methods that best elicit knowledge from large models. Our human study indicates that, though hallucinations exist, large models post the unique advantage of being able to output common sense and summarize facts that cannot be directly retrieved from the search engine. To better exploit such generated knowledge in dialogue generation, we treat the generated knowledge as a noisy knowledge source and propose the posterior-based reweighing as well as the noisy training strategy. Empirical results on two benchmarks show advantages over the state-of-the-art methods.

Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages haven’t been vastly investigated. In this paper, we call attention to a new setting named multilingual keyphrase generation and we contribute two new datasets, EcommerceMKP and AcademicMKP, covering six languages. Technically, we propose a retrieval-augmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages. The retrieval-augmented model leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages. Given a non-English passage, a cross-lingual dense passage retrieval module finds relevant English passages. Then the associated English keyphrases serve as external knowledge for keyphrase generation in the current language. Moreover, we develop a retriever-generator iterative training algorithm to mine pseudo parallel passage pairs to strengthen the cross-lingual passage retriever. Comprehensive experiments and ablations show that the proposed approach outperforms all baselines.

Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems, which rely on large-scale parallel training corpus. In this paper, we present an iterative inplace editing approach for text revision, which requires no parallel data. In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute classification. During inference, the editing at each iteration is realized by two-step span replacement. At the first step, the distributed representation of the text optimizes on the fly towards an attribute function. At the second step, a text span is masked and another new one is proposed conditioned on the optimized representation. The empirical experiments on two typical and important text revision tasks, text formalization and text simplification, show the effectiveness of our approach. It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification, and gains better performance than strong unsupervised methods on text formalization.

Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual data, which we empirically show is sub-optimal. In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data. To this end, we compute the uncertainty of monolingual sentences using the bilingual dictionary extracted from the parallel data. Intuitively, monolingual sentences with lower uncertainty generally correspond to easy-to-translate patterns which may not provide additional gains. Accordingly, we design an uncertainty-based sampling strategy to efficiently exploit the monolingual data for self-training, in which monolingual sentences with higher uncertainty would be sampled with higher probability. Experimental results on large-scale WMT English⇒German and English⇒Chinese datasets demonstrate the effectiveness of the proposed approach. Extensive analyses suggest that emphasizing the learning on uncertain monolingual sentences by our approach does improve the translation quality of high-uncertainty sentences and also benefits the prediction of low-frequency words at the target side.

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks. Code will be released.

Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) knowledge to NAT models, e.g., with knowledge distillation. In this work, we hypothesize and empirically verify that AT and NAT encoders capture different linguistic properties of source sentences. Therefore, we propose to adopt multi-task learning to transfer the AT knowledge to NAT models through encoder sharing. Specifically, we take the AT model as an auxiliary task to enhance NAT model performance. Experimental results on WMT14 En-De and WMT16 En-Ro datasets show that the proposed Multi-Task NAT achieves significant improvements over the baseline NAT models. Furthermore, the performance on large-scale WMT19 and WMT20 En-De datasets confirm the consistency of our proposed method. In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.

The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited in their decision making due to struggles in extracting question-related rules and reasoning about them. In this paper, we present a new framework of conversational machine reading that comprises a novel Explicit Memory Tracker (EMT) to track whether conditions listed in the rule text have already been satisfied to make a decision. Moreover, our framework generates clarification questions by adopting a coarse-to-fine reasoning strategy, utilizing sentence-level entailment scores to weight token-level distributions. On the ShARC benchmark (blind, held-out) testset, EMT achieves new state-of-the-art results of 74.6% micro-averaged decision accuracy and 49.5 BLEU4. We also show that EMT is more interpretable by visualizing the entailment-oriented reasoning process as the conversation flows. Code and models are released at https://github.com/Yifan-Gao/explicit_memory_tracker.

Natural language interfaces to databases(NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programming, it is common for end users to issue questions that are ambiguous to the system or fall outside the semantic scope of its underlying query language. We present PHOTON, a robust, modular, cross-domain NLIDB that can flag natural language input to which a SQL mapping cannot be immediately determined. PHOTON consists of a strong neural semantic parser (63.2% structure accuracy on the Spider dev benchmark), a human-in-the-loop question corrector, a SQL executor and a response generator. The question corrector isa discriminative neural sequence editor which detects confusion span(s) in the input question and suggests rephrasing until a translatable input is given by the user or a maximum number of iterations are conducted. Experiments on simulated data show that the proposed method effectively improves the robustness of text-to-SQL system against untranslatable user input. The live demo of our system is available at http://www.naturalsql.com

Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we explore to identify the inactive training examples which contribute less to the model performance, and show that the existence of inactive examples depends on the data distribution. We further introduce data rejuvenation to improve the training of NMT models on large-scale datasets by exploiting inactive examples. The proposed framework consists of three phases. First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities. Then, we train a rejuvenation model on the active examples, which is used to re-label the inactive examples with forward- translation. Finally, the rejuvenated examples and the active examples are combined to train the final NMT model. Experimental results on WMT14 English-German and English-French datasets show that the proposed data rejuvenation consistently and significantly improves performance for several strong NMT models. Extensive analyses reveal that our approach stabilizes and accelerates the training process of NMT models, resulting in final models with better generalization capability.

Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose “Discern”, a discourse-aware entailment reasoning network to strengthen the connection and enhance the understanding of both document and dialog. Specifically, we split the document into clause-like elementary discourse units (EDU) using a pre-trained discourse segmentation model, and we train our model in a weakly-supervised manner to predict whether each EDU is entailed by the user feedback in a conversation. Based on the learned EDU and entailment representations, we either reply to the user our final decision “yes/no/irrelevant” of the initial question, or generate a follow-up question to inquiry more information. Our experiments on the ShARC benchmark (blind, held-out test set) show that Discern achieves state-of-the-art results of 78.3% macro-averaged accuracy on decision making and 64.0 BLEU1 on follow-up question generation. Code and models are released at https://github.com/Yifan-Gao/Discern.

Social media produces large amounts of contents every day. To help users quickly capture what they need, keyphrase prediction is receiving a growing attention. Nevertheless, most prior efforts focus on text modeling, largely ignoring the rich features embedded in the matching images. In this work, we explore the joint effects of texts and images in predicting the keyphrases for a multimedia post. To better align social media style texts and images, we propose: (1) a novel Multi-Modality MultiHead Attention (M3H-Att) to capture the intricate cross-media interactions; (2) image wordings, in forms of optical characters and image attributes, to bridge the two modalities. Moreover, we design a unified framework to leverage the outputs of keyphrase classification and generation and couple their advantages. Extensive experiments on a large-scale dataset newly collected from Twitter show that our model significantly outperforms the previous state of the art based on traditional attention mechanisms. Further analyses show that our multi-head attention is able to attend information from various aspects and boost classification or generation in diverse scenarios.

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Transformer encoder, and (2) it supports both answer ranking and answer generation seamlessly through the same architecture. More crucially, we adapt BERT for the effective fusion of vision and dialog contents via visually grounded training. Without the need of pretraining on external vision-language data, our model yields new state of the art, achieving the top position in both single-model and ensemble settings (74.54 and 75.35 NDCG scores) on the visual dialog leaderboard. Our code and pretrained models are released at https://github.com/salesforce/VD-BERT.

Sentence function is an important linguistic feature indicating the communicative purpose in uttering a sentence. Incorporating sentence functions into conversations has shown improvements in the quality of generated responses. However, the number of utterances for different types of fine-grained sentence functions is extremely imbalanced. Besides a small number of high-resource sentence functions, a large portion of sentence functions is infrequent. Consequently, dialogue generation conditioned on these infrequent sentence functions suffers from data deficiency. In this paper, we investigate a structured meta-learning (SML) approach for dialogue generation on infrequent sentence functions. We treat dialogue generation conditioned on different sentence functions as separate tasks, and apply model-agnostic meta-learning to high-resource sentence functions data. Furthermore, SML enhances meta-learning effectiveness by promoting knowledge customization among different sentence functions but simultaneously preserving knowledge generalization for similar sentence functions. Experimental results demonstrate that SML not only improves the informativeness and relevance of generated responses, but also can generate responses consistent with the target sentence functions. Code will be public to facilitate the research along this line.

Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task. Unlike the sentence-level text classification problem, the available supervised data for the ERC task is limited, which potentially prevents the models from playing their maximum effect. In this paper, we propose a novel approach to leverage unsupervised conversation data, which is more accessible. Specifically, we propose the Conversation Completion (ConvCom) task, which attempts to select the correct answer from candidate answers to fill a masked utterance in a conversation. Then, we Pre-train a basic COntext-Dependent Encoder (Pre-CODE) on the ConvCom task. Finally, we fine-tune the Pre-CODE on the datasets of ERC. Experimental results demonstrate that pre-training on unsupervised data achieves significant improvement of performance on the ERC datasets, particularly on the minority emotion classes.

Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose to address this gap by focusing on understanding the input-output behavior of NMT models. Specifically, we measure the word importance by attributing the NMT output to every input word through a gradient-based method. We validate the approach on a couple of perturbation operations, language pairs, and model architectures, demonstrating its superiority on identifying input words with higher influence on translation performance. Encouragingly, the calculated importance can serve as indicators of input words that are under-translated by NMT models. Furthermore, our analysis reveals that words of certain syntactic categories have higher importance while the categories vary across language pairs, which can inspire better design principles of NMT architectures for multi-lingual translation.

Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence. A major challenge in QG is to identify answer-relevant context words to finish the declarative-to-interrogative sentence transformation. Existing sequence-to-sequence neural models achieve this goal by proximity-based answer position encoding under the intuition that neighboring words of answers are of high possibility to be answer-relevant. However, such intuition may not apply to all cases especially for sentences with complex answer-relevant relations. Consequently, the performance of these models drops sharply when the relative distance between the answer fragment and other non-stop sentence words that also appear in the ground truth question increases. To address this issue, we propose a method to jointly model the unstructured sentence and the structured answer-relevant relation (extracted from the sentence in advance) for question generation. Specifically, the structured answer-relevant relation acts as the to the point context and it thus naturally helps keep the generated question to the point, while the unstructured sentence provides the full information. Extensive experiments show that to the point context helps our question generation model achieve significant improvements on several automatic evaluation metrics. Furthermore, our model is capable of generating diverse questions for a sentence which conveys multiple relations of its answer fragment.

In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured. We therefore propose a hierarchical Gated Recurrent Unit (HiGRU) framework with a lower-level GRU to model the word-level inputs and an upper-level GRU to capture the contexts of utterance-level embeddings. Moreover, we promote the framework to two variants, Hi-GRU with individual features fusion (HiGRU-f) and HiGRU with self-attention and features fusion (HiGRU-sf), so that the word/utterance-level individual inputs and the long-range contextual information can be sufficiently utilized. Experiments on three dialogue emotion datasets, IEMOCAP, Friends, and EmotionPush demonstrate that our proposed Hi-GRU models attain at least 8.7%, 7.5%, 6.0% improvement over the state-of-the-art methods on each dataset, respectively. Particularly, by utilizing only the textual feature in IEMOCAP, our HiGRU models gain at least 3.8% improvement over the state-of-the-art conversational memory network (CMN) with the trimodal features of text, video, and audio.

Automatic hashtag annotation plays an important role in content understanding for microblog posts. To date, progress made in this field has been restricted to phrase selection from limited candidates, or word-level hashtag discovery using topic models. Different from previous work considering hashtags to be inseparable, our work is the first effort to annotate hashtags with a novel sequence generation framework via viewing the hashtag as a short sequence of words. Moreover, to address the data sparsity issue in processing short microblog posts, we propose to jointly model the target posts and the conversation contexts initiated by them with bidirectional attention. Extensive experimental results on two large-scale datasets, newly collected from English Twitter and Chinese Weibo, show that our model significantly outperforms state-of-the-art models based on classification. Further studies demonstrate our ability to effectively generate rare and even unseen hashtags, which is however not possible for most existing methods.

Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation.

A huge volume of user-generated content is daily produced on social media. To facilitate automatic language understanding, we study keyphrase prediction, distilling salient information from massive posts. While most existing methods extract words from source posts to form keyphrases, we propose a sequence-to-sequence (seq2seq) based neural keyphrase generation framework, enabling absent keyphrases to be created. Moreover, our model, being topic-aware, allows joint modeling of corpus-level latent topic representations, which helps alleviate data sparsity widely exhibited in social media language. Experiments on three datasets collected from English and Chinese social media platforms show that our model significantly outperforms both extraction and generation models without exploiting latent topics. Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.

We study the problem of generating interconnected questions in question-answering style conversations. Compared with previous works which generate questions based on a single sentence (or paragraph), this setting is different in two major aspects: (1) Questions are highly conversational. Almost half of them refer back to conversation history using coreferences. (2) In a coherent conversation, questions have smooth transitions between turns. We propose an end-to-end neural model with coreference alignment and conversation flow modeling. The coreference alignment modeling explicitly aligns coreferent mentions in conversation history with corresponding pronominal references in generated questions, which makes generated questions interconnected to conversation history. The conversation flow modeling builds a coherent conversation by starting questioning on the first few sentences in a text passage and smoothly shifting the focus to later parts. Extensive experiments show that our system outperforms several baselines and can generate highly conversational questions. The code implementation is released at https://github.com/Evan-Gao/conversaional-QG.

This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns (i.e., topics) and those reflecting how participants voice their opinions (i.e., discourse).1 Extensive experiments show that our model can yield both coherent topics and meaningful discourse behavior. Further study shows that our topic and discourse representations can benefit the classification of microblog messages, especially when they are jointly trained with the classifier. Our data sets and code are available at: http://github.com/zengjichuan/Topic_Disc.

Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions. In this work, we introduce a disagreement regularization to explicitly encourage the diversity among multiple attention heads. Specifically, we propose three types of disagreement regularization, which respectively encourage the subspace, the attended positions, and the output representation associated with each attention head to be different from other heads. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation tasks demonstrate the effectiveness and universality of the proposed approach.

Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics.