Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit position bias, i.e., leveraging information positioned at the beginning or end, or specific positional cues within the input. Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality. In this work, we propose a self-supervised position debiasing (SOD) framework to mitigate position bias for LLMs. SOD leverages unsupervised responses from pre-trained LLMs for debiasing without relying on any external knowledge. To improve the quality of unsupervised responses, we propose an objective alignment (OAM) module to prune these responses. Experiments on eight datasets and five tasks show that SOD consistently outperforms existing methods in mitigating three types of position biases. Besides, SOD achieves this by sacrificing only a small performance on biased samples, which is general and effective. To facilitate the reproducibility of the results, we share the code of all methods and datasets on https://github.com/LZKSKY/SOD.

An important unexplored aspect in previous work on user satisfaction estimation for Task-Oriented Dialogue (TOD) systems is their evaluation in terms of robustness for the identification of user dissatisfaction: current benchmarks for user satisfaction estimation in TOD systems are highly skewed towards dialogues for which the user is satisfied. The effect of having a more balanced set of satisfaction labels on performance is unknown. However, balancing the data with more dissatisfactory dialogue samples requires further data collection and human annotation, which is costly and time-consuming. In this work, we leverage large language models (LLMs) and unlock their ability to generate satisfaction-aware counterfactual dialogues to augment the set of original dialogues of a test collection. We gather human annotations to ensure the reliability of the generated samples. We evaluate two open-source LLMs as user satisfaction estimators on our augmented collection against state-of-the-art fine-tuned models. Our experiments show that when used as few-shot user satisfaction estimators, open-source LLMs show higher robustness to the increase in the number of dissatisfaction labels in the test collection than the fine-tuned state-of-the-art models. Our results shed light on the need for data augmentation approaches for user satisfaction estimation in TOD systems. We release our aligned counterfactual dialogues, which are curated by human annotation, to facilitate further research on this topic.

Large Language Models (LLMs) have shown great potential in Natural Language Processing (NLP) tasks.However, recent literature reveals that LLMs hallucinate intermittently, which impedes their reliability for further utilization. In this paper, we propose a novel self-detection method to detect which questions an LLM does not know.Our proposal is empirical and applicable for continually upgrading LLMs compared with state-of-the-art methods. Specifically, we examine the divergence of the LLM’s behaviors on different verbalizations for a question and examine the atypicality of the verbalized input. We combine the two components to identify whether the model generates a non-factual response to the question. The above components can be accomplished by utilizing the LLM itself without referring to any other external resources. We conduct comprehensive experiments and demonstrate the effectiveness of our method for recently released LLMs involving Llama 2, Vicuna, ChatGPT, and GPT-4 across factoid question-answering, arithmetic reasoning, and commonsense reasoning tasks.

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge, which challenges our understanding of their internal mechanisms. In this paper, we devote the first attempt to investigate the layer-wise capability of LLMs through probing tasks. We leverage the powerful generative capability of ChatGPT to construct probing datasets, providing diverse and coherent evidence corresponding to various facts. We employ \mathcal V-usable information as the validation metric to better reflect the capability in encoding context knowledge across different layers. Our experiments on conflicting and newly acquired knowledge show that LLMs: (1) prefer to encode more context knowledge in the upper layers; (2) primarily encode context knowledge within knowledge-related entity tokens at lower layers while progressively expanding more knowledge within other tokens at upper layers; and (3) gradually forget the earlier context knowledge retained within the intermediate layers when provided with irrelevant evidence. Code is publicly available at https://github.com/Jometeorie/probing_llama.

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses due to minor changes in the verbalized instructions. Recent literature has explored this inconsistency issue, highlighting the importance of continued improvement in the robustness of response generation. However, systematic analysis and solutions are still lacking. In this paper, we quantitatively define the inconsistency problem and propose a two-stage training framework consisting of instruction-augmented supervised fine-tuning and consistency alignment training. The first stage helps a model generalize on following instructions via similar instruction augmentations. In the second stage, we improve the diversity and help the model understand which responses are more aligned with human expectations by differentiating subtle differences in similar responses. The training process is accomplished by self-rewards inferred from the trained model at the first stage without referring to external human preference resources. We conduct extensive experiments on recent publicly available LLMs on instruction-following tasks and demonstrate the effectiveness of our training framework.

Parameter-Efficient Fine-tuning (PEFT) facilitates the fine-tuning of Large Language Models (LLMs) under limited resources. However, the fine-tuning performance with PEFT on complex, knowledge-intensive tasks is limited due to the constrained model capacity, which originates from the limited number of additional trainable parameters. To overcome this limitation, we introduce a novel mechanism that fine-tunes LLMs with adapters of larger size yet memory-efficient. This is achieved by leveraging the inherent activation sparsity in the Feed-Forward Networks (FFNs) of LLMs and utilizing the larger capacity of Central Processing Unit (CPU) memory compared to Graphics Processing Unit (GPU). We store and update the parameters of larger adapters on the CPU. Moreover, we employ a Mixture of Experts (MoE)-like architecture to mitigate unnecessary CPU computations and reduce the communication volume between the GPU and CPU. This is particularly beneficial over the limited bandwidth of PCI Express (PCIe). Our method can achieve fine-tuning results comparable to those obtained with larger memory capacities, even when operating under more limited resources such as a 24GB memory single GPU setup, with acceptable loss in training efficiency. Our codes are available at https://github.com/CURRENTF/MEFT.

Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models’ scale and the diversity of tasks increase. Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional, i.e., significant model changes can be represented with relatively few parameters. However, decreasing the rank encounters challenges with generalization errors for specific tasks when compared to full-parameter fine-tuning. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank, thereby offering improved performance potential.The core idea is to freeze original pretrained weights and train a group of mini LoRAs with only a small number of parameters. This can capture a significant degree of diversity among mini LoRAs, thus promoting better generalization ability. We conduct a theoretical analysis and empirical studies on various NLP tasks. Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks, which demonstrates the effectiveness of MELoRA.

Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) for empathetic response generation. Specifically, we employ a novel second-order interaction attention mechanism to iteratively capture vital associated words between dialogue utterances and situations, dialogue history, and a memory module (for storing associated words), thereby accurately and nuancedly comprehending the utterances.We conduct experiments on the Empathetic-Dialogue dataset. Both automatic and human evaluations validate the efficacy of the model. Variant experiments on LLMs also demonstrate that attending to associated words improves empathetic comprehension and expression.

Multi-Hop Question Answering (MHQA) task presents a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair into retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method. To further facilitate future research, we have collected a dataset that traces the reasoning process.

Open-domain multi-turn dialogue generation encounters the significant challenge of lacking various types of knowledge from diverse sources. Existing models typically focus on identifying specific types of dialogue knowledge and utilize corresponding datasets for training. However, this approach often leads to limited generalization capabilities and increased computational resource requirements. Recently, large language models (LLMs) have shown impressive performance on natural language processing tasks. To harness the knowledge storage of LLMs, we propose a framework named KnowEE that explores multi-source multi-type knowledge from LLMs by leveraging diverse datasets and then exploits the obtained knowledge for response generation. Our framework comprises two phases: First, we leverage five external datasets encompassing various types of knowledge to extract the most relevant samples to the dialogue context which are served as prompts to generate corresponding type of knowledge; Second, we inject the acquired knowledge into the ongoing dialogue context in fine-grained and coarse-grained manners, which is then fed into LLMs to generate the final dialogue response. Both automatic and manual evaluation results validate the effectiveness of our framework in exploring and exploiting multi-source multi-type knowledge to generate coherent, informative, and fluent responses.

Legal judgment assistants are developing fast due to impressive progress of large language models (LLMs). However, people can hardly trust the results generated by a model without reliable analysis of legal judgement. For legal practitioners, it is common practice to utilize syllogistic reasoning to select and evaluate the arguments of the parties as part of the legal decision-making process. But the development of syllogistic reasoning for legal judgment analysis is hindered by the lack of resources: (1) there is no large-scale syllogistic reasoning dataset for legal judgment analysis, and (2) there is no set of established benchmarks for legal judgment analysis. In this paper, we construct and manually correct a syllogistic reasoning dataset for legal judgment analysis. The dataset contains 11,239 criminal cases which cover 4 criminal elements, 80 charges and 124 articles. We also select a set of large language models as benchmarks, and conduct a in-depth analysis of the capacity of their legal judgment analysis.

Large Language Models (LLMs) have demonstrated remarkable zero-shot generalization across various language-related tasks, including search engines. However, existing work utilizes the generative ability of LLMs for Information Retrieval (IR) rather than direct passage ranking. The discrepancy between the pre-training objectives of LLMs and the ranking objective poses another challenge. In this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR. Surprisingly, our experiments reveal that properly instructed LLMs can deliver competitive, even superior results to state-of-the-art supervised methods on popular IR benchmarks. Furthermore, to address concerns about data contamination of LLMs, we collect a new test set called NovelEval, based on the latest knowledge and aiming to verify the model’s ability to rank unknown knowledge. Finally, to improve efficiency in real-world applications, we delve into the potential for distilling the ranking capabilities of ChatGPT into small specialized models using a permutation distillation scheme. Our evaluation results turn out that a distilled 440M model outperforms a 3B supervised model on the BEIR benchmark. The code to reproduce our results is available at www.github.com/sunnweiwei/RankGPT.

Answer selection in open-domain dialogues aims to select an accurate answer from candidates. The recent success of answer selection models hinges on training with large amounts of labeled data. However, collecting large-scale labeled data is labor-intensive and time-consuming. In this paper, we introduce the predicted intent labels to calibrate answer labels in a self-training paradigm. Specifically, we propose intent-calibrated self-training (ICAST) to improve the quality of pseudo answer labels through the intent-calibrated answer selection paradigm, in which we employ pseudo intent labels to help improve pseudo answer labels. We carry out extensive experiments on two benchmark datasets with open-domain dialogues. The experimental results show that ICAST outperforms baselines consistently with 1%, 5%, and 10% labeled data. Specifically, it improves 2.06% and 1.00% of F1 score on the two datasets, compared with the strongest baseline with only 5% labeled data.

Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to classify each candidate snippet as “relevant” or “irrelevant” independently. However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets. Moreover, they lack modeling of the discourse structure of dialogue-knowledge interactions. We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. GenKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogue-knowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.

Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) reference-based: evaluating with human-labeled reference summary; (2) reference-free: evaluating the summary consistency of the document. Recent studies mainly focus on one of these scenarios and explore training neural models built on PLMs to align with human criteria. However, the models from different scenarios are optimized individually, which may result in sub-optimal performance since they neglect the shared knowledge across different scenarios. Besides, designing individual models for each scenario caused inconvenience to the user. Inspired by this, we propose Unified Multi-scenario Summarization Evaluation Model (UMSE). More specifically, we propose a perturbed prefix tuning method to share cross-scenario knowledge between scenarios and use a self-supervised training paradigm to optimize the model without extra human labeling. Our UMSE is the first unified summarization evaluation framework engaged with the ability to be used in three evaluation scenarios. Experimental results across three typical scenarios on the benchmark dataset SummEval indicate that our UMSE can achieve comparable performance with several existing strong methods which are specifically designed for each scenario.

Multiple defendants in a criminal fact description generally exhibit complex interactions, and cannot be well handled by existing Legal Judgment Prediction (LJP) methods which focus on predicting judgment results (e.g., law articles, charges, and terms of penalty) for single-defendant cases. To address this problem, we propose the task of multi-defendant LJP, which aims to automatically predict the judgment results for each defendant of multi-defendant cases. Two challenges arise with the task of multi-defendant LJP: (1) indistinguishable judgment results among various defendants; and (2) the lack of a real-world dataset for training and evaluation. To tackle the first challenge, we formalize the multi-defendant judgment process as hierarchical reasoning chains and introduce a multi-defendant LJP method, named Hierarchical Reasoning Network (HRN), which follows the hierarchical reasoning chains to determine criminal relationships, sentencing circumstances, law articles, charges, and terms of penalty for each defendant. To tackle the second challenge, we collect a real-world multi-defendant LJP dataset, namely MultiLJP, to accelerate the relevant research in the future. Extensive experiments on MultiLJP verify the effectiveness of our proposed HRN.

Few-shot named entity recognition (NER) has shown remarkable progress in identifying entities in low-resource domains. However, few-shot NER methods still struggle with out-of-domain (OOD) examples due to their reliance on manual labeling for the target domain. To address this limitation, recent studies enable generalization to an unseen target domain with only a few labeled examples using data augmentation techniques. Two important challenges remain: First, augmentation is limited to the training data, resulting in minimal overlap between the generated data and OOD examples. Second, knowledge transfer is implicit and insufficient, severely hindering model generalizability and the integration of knowledge from the source domain. In this paper, we propose a framework, prompt learning with type-related features (PLTR), to address these challenges. To identify useful knowledge in the source domain and enhance knowledge transfer, PLTR automatically extracts entity type-related features (TRFs) based on mutual information criteria. To bridge the gap between training and OOD data, PLTR generates a unique prompt for each unseen example by selecting relevant TRFs. We show that PLTR achieves significant performance improvements on in-domain and cross-domain datasets. The use of PLTR facilitates model adaptation and increases representation similarities between the source and unseen domains.

Empathetic response generation aims to generate empathetic responses by understanding the speaker’s emotional feelings from the language of dialogue. Recent methods capture emotional words in the language of communicators and construct them as static vectors to perceive nuanced emotions. However, linguistic research has shown that emotional words in language are dynamic and have correlations with other grammar semantic roles, i.e., words with semantic meanings, in grammar. Previous methods overlook these two characteristics, which easily lead to misunderstandings of emotions and neglect of key semantics. To address this issue, we propose a dynamical Emotion-Semantic Correlation Model (ESCM) for empathetic dialogue generation tasks. ESCM constructs dynamic emotion-semantic vectors through the interaction of context and emotions. We introduce dependency trees to reflect the correlations between emotions and semantics. Based on dynamic emotion-semantic vectors and dependency trees, we propose a dynamic correlation graph convolutional network to guide the model in learning context meanings in dialogue and generating empathetic responses. Experimental results on the EMPATHETIC-DIALOGUES dataset show that ESCM understands semantics and emotions more accurately and expresses fluent and informative empathetic responses. Our analysis results also indicate that the correlations between emotions and semantics are frequently used in dialogues, which is of great significance for empathetic perception and expression.

The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.

Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence or the dialogues are conversed between annotators far from real user settings. In this paper, we release a large-scale dialogue quality assessment dataset (DiQAD), for automatically assessing open-domain dialogue quality. Specifically, we (1) establish the assessment criteria based on the dimensions conforming to human judgements on dialogue qualities, and (2) annotate large-scale dialogues that conversed between real users based on these annotation criteria, which contains around 100,000 dialogues. We conduct several experiments and report the performances of the baselines as the benchmark on DiQAD. The dataset is openly accessible at https://github.com/yukunZhao/Dataset_Dialogue_quality_evaluation.

In open-domain question answering, due to the ambiguity of questions, multiple plausible answers may exist. To provide feasible answers to an ambiguous question,one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity. An alternative is to gather candidate answers and aggregate them, but this method can be computationally costly and may neglect dependencies among answers. In this paper, we present AmbigPrompt to address the imperfections of existing approaches to answering ambiguous questions. Specifically, we integrate an answering model with a prompting model in an iterative manner. The prompting model adaptively tracks the reading process and progressively triggers the answering model to compose distinct and relevant answers. Additionally, we develop a task-specific post-pretraining approach for both the answering model and the prompting model, which greatly improves the performance of our framework. Empirical studies on two commonly-used open benchmarks show that AmbigPrompt achieves state-of-the-art or competitive results while using less memory and having a lower inference latency than competing approaches. Additionally, AmbigPrompt also performs well in low-resource settings.

Evaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need better consistency with humans, while reliable human evaluation can be time- and cost-intensive. To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem. Specifically, RADE explicitly compares reference and the candidate response to predict their overall scores. Moreover, an auxiliary response generation task enhances prediction via a shared encoder. To support RADE, we extend three datasets with additional rated responses other than just a golden response by human annotation. Experiments on our three datasets and two existing benchmarks demonstrate the effectiveness of our method, where Pearson, Spearman, and Kendall correlations with human evaluation outperform state-of-the-art baselines.

Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new challenges to the neural auto-regressive text generators nowadays. Despite these neural models are good at producing human-like text, it is difficult for them to arrange causalities and relations between given facts and possible ensuing events. To bridge this gap, we propose a novel two-stage method which explicitly arranges the ensuing events in open-ended text generation. Our approach can be understood as a specially-trained coarse-to-fine algorithm, where an event transition planner provides a “coarse” plot skeleton and a text generator in the second stage refines the skeleton. Experiments on two open-ended text generation tasks demonstrate that our proposed method effectively improves the quality of the generated text, especially in coherence and diversity. We will release the codes to the community for further exploration.

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation based methods often get trapped in easily learned tokens as all tokens are treated equally during training. In this work, we introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. To train RISE, we devise an Iterative Reinforce Training (IRT) algorithm with a Dynamic Programming based Sampling (DPS) process to improve exploration. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods and generalizes well on unseen data.

A humanized dialogue system is expected to generate empathetic replies, which should be sensitive to the users’ expressed emotion. The task of empathetic dialogue generation is proposed to address this problem. The essential challenges lie in accurately capturing the nuances of human emotion and considering the potential of user feedback, which are overlooked by the majority of existing work. In response to this problem, we propose a multi-resolution adversarial model – EmpDG, to generate more empathetic responses. EmpDG exploits both the coarse-grained dialogue-level and fine-grained token-level emotions, the latter of which helps to better capture the nuances of user emotion. In addition, we introduce an interactive adversarial learning framework which exploits the user feedback, to identify whether the generated responses evoke emotion perceptivity in dialogues. Experimental results show that the proposed approach significantly outperforms the state-of-the-art baselines in both content quality and emotion perceptivity.

Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility. We propose a novel, holistic, extendable framework based on a single sequence-to-sequence (seq2seq) model which can be optimized with supervised or reinforcement learning. A key contribution is that we design text spans named belief spans to track dialogue believes, allowing task-oriented dialogue systems to be modeled in a seq2seq way. Based on this, we propose a simplistic Two Stage CopyNet instantiation which emonstrates good scalability: significantly reducing model complexity in terms of number of parameters and training time by a magnitude. It significantly outperforms state-of-the-art pipeline-based methods on large datasets and retains a satisfactory entity match rate on out-of-vocabulary (OOV) cases where pipeline-designed competitors totally fail.

End-to-end neural dialogue generation has shown promising results recently, but it does not employ knowledge to guide the generation and hence tends to generate short, general, and meaningless responses. In this paper, we propose a neural knowledge diffusion (NKD) model to introduce knowledge into dialogue generation. This method can not only match the relevant facts for the input utterance but diffuse them to similar entities. With the help of facts matching and entity diffusion, the neural dialogue generation is augmented with the ability of convergent and divergent thinking over the knowledge base. Our empirical study on a real-world dataset prove that our model is capable of generating meaningful, diverse and natural responses for both factoid-questions and knowledge grounded chi-chats. The experiment results also show that our model outperforms competitive baseline models significantly.