Controversy is widespread online. Previous studies mainly define controversy based on vague assumptions of its relation to sentiment such as hate speech and offensive words. This paper introduces the first question-answering dataset that defines content controversy by user perception, i.e., votes from plenty of users. It contains nearly 10K questions, and each question has a best answer and a most controversial answer. Experimental results reveal that controversy detection in question answering is essential and challenging, and there is no strong correlation between controversy and sentiment tasks. We also show that controversial answers and most acceptable answers cannot be distinguished by retrieval-based QA models, which may cause controversy issues. With these insights, we believe ControversialQA can inspire future research on controversy in QA systems.

Large language models (LLMs) have shown remarkable reasoning capabilities, particularly with Chain-of-Thought-style prompts. However, LLMs can still struggle with problems that are easy for humans, such as generating action plans for executing tasks or performing complex math or logical reasoning. This is due to LLMs’ absence of an internal world model for predicting world states (e.g., environment status, variable values) and simulating long-term action outcomes of actions. This prevents LLMs from performing deliberate planning akin to human brains, which involves exploring alternative reasoning paths, anticipating future states and rewards, and iteratively refining existing reasoning steps. To overcome the limitations, we propose a new LLM reasoning framework, Reasoning via Planning (RAP). RAP repurposes the LLM as both a world model and a reasoning agent, and incorporates a principled planning algorithm (based on Monte Carlo Tree Search) for strategic exploration in the vast reasoning space. During reasoning, the LLM (as agent) incrementally builds a reasoning tree under the guidance of the LLM (as world model) and task-specific rewards, properly balancing exploration v.s. exploitation to achieve a high-reward reasoning path efficiently. We apply RAP to a variety of challenging reasoning problems, such as plan generation, math reasoning, and logical inference. Empirical results demonstrate the superiority of RAP over various strong baselines, including CoT and least-to-most prompting with self-consistency, e.g., RAP on LLaMA-33B surpasses CoT on GPT-4 with 33% relative improvement in plan generation.

We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps. Covering a wide range of cooking and how-to tasks, we aim to deliver a collaborative and engaging dialogue experience. Equipped with language understanding, dialogue management, and response generation components supported by a robust search engine, TacoBot ensures efficient task assistance. To enhance the dialogue experience, we explore a series of data augmentation strategies using LLMs to train advanced neural models continuously. TacoBot builds upon our successful participation in the inaugural Alexa Prize TaskBot Challenge, where our team secured third place among ten competing teams. We offer TacoBot as an open-source framework that serves as a practical example for deploying task-oriented dialogue systems.

Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited from such knowledge transfer because of its distinct formulation, i.e., tracking the event flow while following structural constraints. State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results. To this end, we propose MeeT, a Multi-task learning-enabled entity Tracking approach, which utilizes knowledge gained from general domain tasks to improve entity tracking. Specifically, MeeT first fine-tunes T5, a pre-trained multi-task learning model, with entity tracking-specialized QA formats, and then employs our customized decoding strategy to satisfy the structural constraints. MeeT achieves state-of-the-art performances on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.

Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context (few-shot in-context learning). However, recent studies show that even the more advanced LLMs fail in scenarios that require reasoning over multiple objects or facts and making sequences of logical deductions. We propose a two-stage probabilistic inference paradigm, ThinkSum, which reasons over sets of objects or facts in a structured manner. In the first stage (Think – retrieval of associations), a LLM is queried in parallel over a set of phrases extracted from the prompt or an auxiliary model call. In the second stage (Sum – probabilistic inference or reasoning), the results of these queries are aggregated to make the final prediction. We demonstrate the possibilities and advantages of ThinkSum on the BIG-bench suite of LLM evaluation tasks, achieving improvements over the state of the art using GPT-family models on thirteen difficult tasks, often with far smaller model variants. We also compare and contrast ThinkSum with other proposed modifications to direct prompting of LLMs, such as variants of chain-of-thought prompting. Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs. Overall, our proposed paradigm represents a promising approach for enhancing the reasoning capabilities of LLMs.

Prompt-based learning, which exploits knowledge from pre-trained language models by providing textual prompts and designing appropriate answer-category mapping methods, has achieved impressive successes on few-shot text classification and natural language inference (NLI). Because of the diverse linguistic expression, there exist many answer tokens for the same category. However, both manual answer design and automatic answer search constrain answer space and therefore hardly achieve ideal performance. To address this issue, we propose an answer space clustered prompting model (ASCM) together with a synonym initialization method (SI) which automatically categorizes all answer tokens in a semantic-clustered embedding space. We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models. Extensive experiments demonstrate that our ASCM+SL significantly outperforms existing state-of-the-art techniques in few-shot settings.

Quality control is essential for creating extractive question answering (EQA) datasets via crowdsourcing. Aggregation across answers, i.e. word spans within passages annotated, by different crowd workers is one major focus for ensuring its quality. However, crowd workers cannot reach a consensus on a considerable portion of questions. We introduce a simple yet effective answer aggregation method that takes into account the relations among the answer, question, and context passage. We evaluate answer quality from both the view of question answering model to determine how confident the QA model is about each answer and the view of the answer verification model to determine whether the answer is correct. Then we compute aggregation scores with each answer’s quality and its contextual embedding produced by pre-trained language models. The experiments on a large real crowdsourced EQA dataset show that our framework outperforms baselines by around 16% on precision and effectively conduct answer aggregation for extractive QA task.

Completing missing facts is a fundamental task for temporal knowledge graphs (TKGs).Recently, graph neural network (GNN) based methods, which can simultaneously explore topological and temporal information, have become the state-of-the-art (SOTA) to complete TKGs. However, these studies are based on hand-designed architectures and fail to explore the diverse topological and temporal properties of TKG.To address this issue, we propose to use neural architecture search (NAS) to design data-specific message passing architecture for TKG completion.In particular, we develop a generalized framework to explore topological and temporal information in TKGs.Based on this framework, we design an expressive search space to fully capture various properties of different TKGs. Meanwhile, we adopt a search algorithm, which trains a supernet structure by sampling single path for efficient search with less cost.We further conduct extensive experiments on three benchmark datasets. The results show that the searched architectures by our method achieve the SOTA performances.Besides, the searched models can also implicitly reveal diverse properties in different TKGs.Our code is released in https://github.com/striderdu/SPA.

In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialogue system is distinguished from existing single-purpose human-machine dialog systems, as it combines task-oriented and chit-chats with uniqueness in dialogue topics and procedures. However, due to the social stigma associated with mental illness, the dialogue data related to depression consultation and diagnosis are rarely disclosed. Based on clinical depression diagnostic criteria ICD-11 and DSM-5, we designed a 3-phase procedure to construct D⁴: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat, which simulates the dialogue between doctors and patients during the diagnosis of depression, including diagnosis results and symptom summary given by professional psychiatrists for each conversation. Upon the newly-constructed dataset, four tasks mirroring the depression diagnosis process are established: response generation, topic prediction, dialog summary, and severity classification of depressive episode and suicide risk. Multi-scale evaluation results demonstrate that a more empathy-driven and diagnostic-accurate consultation dialogue system trained on our dataset can be achieved compared to rule-based bots.

Multi-hop question answering (QA) combines multiple pieces of evidence to search for the correct answer. Reasoning over a text corpus (TextQA) and/or a knowledge base (KBQA) has been extensively studied and led to distinct system architectures. However, knowledge transfer between such two QA systems has been under-explored. Research questions like what knowledge is transferred or whether the transferred knowledge can help answer over one source using another one, are yet to be answered. In this paper, therefore, we study the knowledge transfer of multi-hop reasoning between structured and unstructured sources. We first propose a unified QA framework named SimultQA to enable knowledge transfer and bridge the distinct supervisions from KB and text sources. Then, we conduct extensive analyses to explore how knowledge is transferred by leveraging the pre-training and fine-tuning paradigm. We focus on the low-resource fine-tuning to show that pre-training SimultQA on one source can substantially improve its performance on the other source. More fine-grained analyses on transfer behaviors reveal the types of transferred knowledge and transfer patterns. We conclude with insights into how to construct better QA datasets and systems to exploit knowledge transfer for future work.

Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present coherence boosting, an inference procedure that increases a LM’s focus on a long context. We show the benefits of coherence boosting with pretrained models by distributional analyses of generated ordinary text and dialog responses. It is also found that coherence boosting with state-of-the-art models for various zero-shot NLP tasks yields performance gains with no additional training.

Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11%. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.

This paper describes the system submitted to SemEval 2021 Task 5: Toxic Spans Detection. The task concerns evaluating systems that detect the spans that make a text toxic when detecting such spans are possible. To address the possibly multi-span detection problem, we develop a start-to-end tagging framework on top of RoBERTa based language model. Besides, we design a custom loss function that takes distance into account. In comparison to other participating teams, our system has achieved 69.03% F1 score, which is slightly lower (-1.8 and -1.73) than the top 1(70.83%) and top 2 (70.77%), respectively.

Nowadays, the interpretability of machine learning models is becoming increasingly important, especially in the medical domain. Aiming to shed some light on how to rationalize medical relation prediction, we present a new interpretable framework inspired by existing theories on how human memory works, e.g., theories of recall and recognition. Given the corpus-level statistics, i.e., a global co-occurrence graph of a clinical text corpus, to predict the relations between two entities, we first recall rich contexts associated with the target entities, and then recognize relational interactions between these contexts to form model rationales, which will contribute to the final prediction. We conduct experiments on a real-world public clinical dataset and show that our framework can not only achieve competitive predictive performance against a comprehensive list of neural baseline models, but also present rationales to justify its prediction. We further collaborate with medical experts deeply to verify the usefulness of our model rationales for clinical decision making.

Generating questions based on answers and relevant contexts is a challenging task. Recent work mainly pays attention to the quality of a single generated question. However, question generation is actually a one-to-many problem, as it is possible to raise questions with different focuses on contexts and various means of expression. In this paper, we explore the diversity of question generation and come up with methods from these two aspects. Specifically, we relate contextual focuses with content selectors, which are modeled by a continuous latent variable with the technique of conditional variational auto-encoder (CVAE). In the realization of CVAE, a multimodal prior distribution is adopted to allow for more diverse content selectors. To take into account various means of expression, question types are explicitly modeled and a diversity-promoting algorithm is proposed further. Experimental results on public datasets show that our proposed method can significantly improve the diversity of generated questions, especially from the perspective of using different question types. Overall, our proposed method achieves a better trade-off between generation quality and diversity compared with existing approaches.

While sophisticated neural-based techniques have been developed in reading comprehension, most approaches model the answer in an independent manner, ignoring its relations with other answer candidates. This problem can be even worse in open-domain scenarios, where candidates from multiple passages should be combined to answer a single question. In this paper, we formulate reading comprehension as an extract-then-select two-stage procedure. We first extract answer candidates from passages, then select the final answer by combining information from all the candidates. Furthermore, we regard candidate extraction as a latent variable and train the two-stage process jointly with reinforcement learning. As a result, our approach has improved the state-of-the-art performance significantly on two challenging open-domain reading comprehension datasets. Further analysis demonstrates the effectiveness of our model components, especially the information fusion of all the candidates and the joint training of the extract-then-select procedure.