Characters are at the heart of every story, driving the plot and engaging readers. In this study, we explore the understanding of characters in full-length books, which contain complex narratives and numerous interacting characters. We define two tasks: character description, which generates a brief factual profile, and character analysis, which offers an in-depth interpretation, including character development, personality, and social context. We introduce the BookWorm dataset, pairing books from the Gutenberg Project with human-written descriptions and analyses. Using this dataset, we evaluate state-of-the-art long-context models in zero-shot and fine-tuning settings, utilizing both retrieval-based and hierarchical processing for book-length inputs. Our findings show that retrieval-based approaches outperform hierarchical ones in both tasks. Additionally, fine-tuned models using coreference-based retrieval produce the most factual descriptions, as measured by fact- and entailment-based metrics. We hope our dataset, experiments, and analysis will inspire further research in character-based narrative understanding.
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over the context, then assigns each step to program-based or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and fine-tuning methods. GPT-3.5-Turbo following Plan-then-Reason framework surpasses other prompting baselines without self-consistency while using less API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of fine-tuning with this framework. We present ProTrix model family by finetuning models on TrixInstruct. Our experiments show that ProTrix family generalizes to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that ProTrix can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We will open-source our dataset and models.
Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models
PDF ↗Emotions play important epistemological and cognitive roles in our lives, revealing our values and guiding our actions. Previous work has shown that LLMs display biases in emotion attribution along gender lines. However, unlike gender, which says little about our values, religion, as a socio-cultural system, prescribes a set of beliefs and values for its followers. Religions, therefore, cultivate certain emotions. Moreover, these rules are explicitly laid out and interpreted by religious leaders. Using emotion attribution, we explore how different religions are represented in LLMs. We find that:Major religions in the US and European countries are represented with more nuance, displaying a more shaded model of their beliefs.Eastern religions like Hinduism and Buddhism are strongly stereotyped.Judaism and Islam are stigmatized – the models’ refusal skyrocket. We ascribe these to cultural bias in LLMs and the scarcity of NLP literature on religion. In the rare instances where religion is discussed, it is often in the context of toxic language, perpetuating the perception of these religions as inherently toxic. This finding underscores the urgent need to address and rectify these biases. Our research emphasizes the crucial role emotions play in shaping our lives and how our values influence them.
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the model to adjust its internal parameters based on the data. However, this paper presents a counterintuitive finding: For tasks with implicit patterns, ICL captures these patterns significantly better than fine-tuning. We developed several datasets featuring implicit patterns, such as sequences determining answers through parity or identifying reducible terms in calculations. We then evaluated the models’ understanding of these patterns under both fine-tuning and ICL across models ranging from 0.5B to 7B parameters. The results indicate that models employing ICL can quickly grasp deep patterns and significantly improve accuracy. In contrast, fine-tuning, despite utilizing thousands of times more training samples than ICL, achieved only limited improvements. We also proposed circuit shift theory from a mechanistic interpretability’s view to explain why ICL wins.
Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
PDF ↗Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts due to they discard some information to reduce computational overhead. In this work, we propose a simple yet effective method to enable LLMs to take a deep breath, encouraging them to summarize information contained within discrete text chunks. Specifically, we segment the text into multiple chunks and insert special token <SR> at the end of each chunk. We then modify the attention mask to integrate the chunk’s information into the corresponding <SR> token. This facilitates LLMs to interpret information not only from historical individual tokens but also from the <SR> token, aggregating the chunk’s semantic information. Experiments on language modeling and out-of-domain downstream tasks validate the superiority of our approach.
Automatic factuality verification of large language model (LLM) generations is becoming more and more widely used to combat hallucinations. A major point of tension in the literature is the granularity of this fact-checking: larger chunks of text are hard to fact-check, but more atomic facts like propositions may lack context to interpret correctly. In this work, we assess the role of context in these atomic facts. We argue that fully atomic facts are not the right representation, and define two criteria for molecular facts: decontextuality, or how well they can stand alone, and minimality, or how little extra information is added to achieve decontexuality. We quantify the impact of decontextualization on minimality, then present a baseline methodology for generating molecular facts automatically, aiming to add the right amount of information. We compare against various methods of decontextualization and find that molecular facts balance minimality with fact verification accuracy in ambiguous settings.
SummaCoz: A Dataset for Improving the Interpretability of Factual Consistency Detection for Summarization
PDF ↗Summarization is an important application of Large Language Models (LLMs). When judging the quality of a summary, factual consistency holds a significant weight. Despite numerous efforts dedicated to building factual inconsistency detectors, the exploration of explanability remains limited among existing effort. In this study, we incorporate both human-annotated and model-generated natural language explanations elucidating how a summary deviates and thus becomes inconsistent with its source article. We build our explanation-augmented dataset on top of the widely used SummaC summarization consistency benchmark. Additionally, we develop an inconsistency detector that is jointly trained with the collected explanations. Our findings demonstrate that integrating explanations during training not only enables the model to provide rationales for its judgments but also enhances its accuracy significantly.
The prevalent use of large language models (LLMs) in various domains has drawn attention to the issue of “hallucination”, which refers to instances where LLMs generate factually inaccurate or ungrounded information. Existing techniques usually identify hallucinations post-generation that cannot prevent their occurrence and suffer from inconsistent performance due to the influence of the instruction format and model style. In this paper, we introduce a novel pre-detection self-evaluation technique, referred to as SELF-FAMILIARITY, which focuses on evaluating the model’s familiarity with the concepts present in the input instruction and withholding the generation of response in case of unfamiliar concepts under the zero-resource setting, where external ground-truth or background information is not available. We also propose a new dataset Concept-7 focusing on the hallucinations caused by limited inner knowledge. We validate SELF-FAMILIARITY across four different large language models, demonstrating consistently superior performance compared to existing techniques. Our findings propose a significant shift towards preemptive strategies for hallucination mitigation in LLM assistants, promising improvements in reliability, applicability, and interpretability.
Exploring Question Guidance and Answer Calibration for Visually Grounded Video Question Answering
PDF ↗Video Question Answering (VideoQA) tasks require not only correct answers but also visual evidence. The “localize-then-answer” strategy, while enhancing accuracy and interpretability, faces challenges due to the lack of temporal localization labels in VideoQA datasets. Existing methods often train the models’ localization capabilities indirectly using QA labels, leading to inaccurate localization. Moreover, our experiments show that despite high accuracy, current models depend too heavily on language shortcuts or spurious correlations with irrelevant visual context. To address these issues, we propose a Question-Guided and Answer-Calibrated TRansformer (QGAC-TR), which guides and calibrates localization using question and option texts without localization labels. Furthermore, we design two self-supervised learning tasks to further enhance the model’s refined localization capabilities. Extensive experiments on three public datasets focused on temporal and causal reasoning show that our model not only achieves accuracy comparable to large-scale pretrained models but also leads in localization aspects. Code will be available on GitHub.
It has been well recognized that text classification can be satisfactorily performed by Deep Neural Network (DNN) models, provided that there are sufficient in-distribution training data. However, in the presence of distribution drift, a well trained DNN model may not perform well on a new dataset even though class labels are aligned between training and target datasets. To alleviate this limitation, we propose a novel approach based on model risk analysis to adapt a pre-trained DNN model towards a new dataset given only a small set of representative data. We first present a solution of model risk analysis for text classification, which can effectively quantify misprediction risk of a classifier on a dataset. Built upon the existing framework of LearnRisk, the proposed solution, denoted by LearnRisk-TC, first generates interpretable risk features, then constructs a risk model by aggregating these features, and finally trains the risk model on a small set of labeled data. Furthermore, we present a transfer learning solution based on model risk analysis, which can effectively fine-tune a pre-trained model toward a target dataset by minimizing its misprediction risk. We have conducted extensive experiments on real datasets. Our experimental results show that the proposed solution performs considerably better than the existing alternative approaches. By using text classification as a test case, we demonstrate the potential applicability of risk-based transfer learning to various challenging NLP tasks. Our codes are available at https://github.com/syjcomputer/LRTC.
As intelligent education evolves, it will provide students with multiple personalized learning services based on their individual abilities. Computerized adaptive testing (CAT) is designed to accurately measure a student’s ability using the least questions, providing an efficient and personalized testing method. However, existing methods mainly focus on minimizing the number of questions required to assess ability, often lacking clear and reliable explanations for the question selection process. Educators and students can hardly trust and accept CAT systems without an understanding of the rationale behind the question selection process. To address this issue, we introduce LLM-Agent-Based CAT (LACAT), a novel agent powered by large language models to enhance CAT with human-like interpretability and explanation capabilities. LACAT consists of three key modules: the Summarizer, which generates interpretable student profiles; the Reasoner, which personalizes questions and provides human-readable explanations; and the Critic, which learns from past choices to optimize future question selection. We conducted extensive experiments on three real-world educational datasets. The results demonstrate that LACAT can perform comparably or superior to traditional CAT methods in accuracy and significantly improve the transparency and acceptability of the testing process. Human evaluations further confirm that LACAT can generate high-quality, understandable explanations, thereby enhancing student trust and satisfaction.
With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach to mitigate these costs is compressing the long input contexts. Existing methods typically leverage the self-attention mechanism of the large model itself for context compression. While these methods have achieved notable results, the compression process still entails quadratic complexity. To mitigate this limitation, we propose the In-Context Former (IC-Former). This method does not rely on the target large model but instead utilizes cross-attention mechanisms to extract and condense information from the contextual embeddings. The computational overhead of our method grows linearly with the compression range. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times while achieving 90% of the baseline performance on evaluation metrics. Additionally, IC-Former demonstrates strong regularity in its interactions with the context, enhancing its interpretability. Overall, IC-Former significantly reduces compression costs, making real-time compression scenarios feasible.
MGCL: Multi-Granularity Clue Learning for Emotion-Cause Pair Extraction via Cross-Grained Knowledge Distillation
PDF ↗Emotion-cause pair extraction (ECPE) aims to identify emotion clauses and their corresponding cause clauses within a document. Traditional methods often rely on coarse-grained clause-level annotations, which can overlook valuable fine-grained clues. To address this issue, we propose Multi-Granularity Clue Learning (MGCL), a novel approach designed to capture fine-grained emotion-cause clues from a weakly-supervised perspective efficiently. In MGCL, a teacher model is leveraged to give sub-clause clues without needing fine-grained annotated labels and guides a student model to identify clause-level emotion-cause pairs. Furthermore, we explore domain-invariant extra-clause clues under the teacher model’s advice to enhance the learning process. Experimental results on the benchmark dataset demonstrate that our method achieves state-of-the-art performance while offering improved interpretability.
Fine-grained image classification, especially in zero-/few-shot scenarios, poses a considerable challenge for vision-language models (VLMs) like CLIP, which often struggle to differentiate between semantically similar classes due to insufficient supervision for fine-grained tasks. On the other hand, Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in tasks like Visual Question Answering (VQA) but remain underexplored in the context of fine-grained image classification. This paper presents CascadeVLM, a novel framework that harnesses the complementary strengths of both CLIP-like and LVLMs VLMs to tackle these challenges. Using granular knowledge effectively in LVLMs and integrating a cascading approach, CascadeVLM dynamically allocates samples using an entropy threshold, balancing computational efficiency with classification accuracy. Experiments on multiple fine-grained datasets, particularly the Stanford Cars dataset, show that CascadeVLM outperforms existing models, achieving 92% accuracy. Our results highlight the potential of combining VLM and LVLM for robust, efficient and interpretable fine-grained image classification, offering new insights into their synergy.
Large Vision-Language Models (VLMs) have already been applied to the understanding of Graphical User Interfaces (GUIs) and have achieved notable results. However, existing VLMs often overly rely on internal text-based knowledge while neglecting visual inputs. This imbalance may lead models to produce answers that do not align with the visual content in GUI comprehension tasks. Such inaccuracies are termed as ‘hallucinations’ where models generate incorrect or illogical responses upon visual verification against GUI elements. These errors result in misinterpretations and diminish the model’s practical utility in applied settings. To address these issues, we introduce VGA, a fine-tuned model designed for comprehensive GUI understanding. Our model aims to balance attention image and text to enhance interpretation and reduce hallucinations. We construct a Vision Question Answering (VQA) dataset of 63.8k high-quality examples with our propose *Referent Method*, focusing on response with visual content of images. We then design a two-stage fine-tuning method to enhance both the model’s accuracy to extract information from image content and alignment with human intent. Experiments show that our approach enhances the model’s ability to extract information from images and achieves state-of-the-art results in GUI understanding tasks. https://github.com/Linziyang1999/VGA-visual-GUI-assistant
The deployment of Large Language Models (LLMs) in content generation raises significant safety concerns, particularly regarding the transparency and interpretability of content evaluations. Current methods, primarily focused on binary safety classifications, lack mechanisms for detailed critique, limiting their utility for model improvement and user trust. To address these limitations, we introduce SAFETY-J, a bilingual generative safety evaluator for English and Chinese with critique-based judgment. SAFETY-J utilizes a robust training dataset that includes diverse dialogues and augmented query-response pairs to assess safety across various scenarios comprehensively. We establish an automated meta-evaluation benchmark that objectively assesses the quality of critiques with minimal human intervention, facilitating scalable and continuous improvement. Additionally, SAFETY-Jemploys an iterative preference learning technique to dynamically refine safety assessments based on meta-evaluations and critiques. Our evaluations demonstrate that SAFETY-J provides more nuanced and accurate safety evaluations, thereby enhancing both critique quality and predictive reliability in complex content scenarios. To facilitate further research and application, we have released SAFETY-J’s training protocols, datasets, and code at https://github.com/GAIR-NLP/Safety-J.
MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems
PDF ↗Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models have demonstrated remarkable abilities in visual reasoning and mathematical tasks, there is little work on investigating whether these models can effectively interpret visual elements for code generation. To this end, we present MMCode, the first multi-modal coding dataset for evaluating algorithmic problem-solving skills in visually rich contexts. MMCode contains 3,548 questions and 6,620 images collected from real-world programming challenges harvested from 10 code competition websites, presenting significant challenges due to the extreme demand for reasoning abilities. Our experiment results show that current state-of-the-art models struggle to solve these problems. The results highlight the lack of powerful vision-code models, and we hope MMCode can serve as an inspiration for future works in this domain. The data and code are publicly available.
The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper explores elevating the quality of existing instruction data to better align with human values, introducing a simple and effective approach named ReAlign, which reformats the responses of instruction data into a format that better aligns with pre-established criteria and the collated evidence. This approach minimizes human annotation, hallucination, and the difficulty in scaling, remaining orthogonal to existing alignment techniques. Experimentally, ReAlign significantly boosts the general alignment ability, math reasoning, factuality, and readability of the LLMs.Encouragingly, without introducing any additional data or advanced training techniques, and merely by reformatting the response, LLaMA-2-13B’s mathematical reasoning ability on GSM8K can be improved **from 46.77% to 56.63%** in accuracy. Additionally, a mere 5% of ReAlign data yields a 67% boost in general alignment ability measured by the Alpaca dataset. This work highlights the need for further research into the science and mechanistic interpretability of LLMs. We have made the associated code and data publicly accessible to support future studies at https://github.com/GAIR-NLP/ReAlign.
Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (ICA) is identified as an effective solution. ICA-transformed word embeddings reveal interpretable semantic axes; however, the order of these axes are arbitrary. In this study, we focus on this property and propose a novel method, Axis Tour, which optimizes the order of the axes. Inspired by Word Tour, a one-dimensional word embedding method, we aim to improve the clarity of the word embedding space by maximizing the semantic continuity of the axes. Furthermore, we show through experiments on downstream tasks that Axis Tour yields better or comparable low-dimensional embeddings compared to both PCA and ICA.
We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains. The LLM is prompted to answer these questionnaires by impersonating the interviewee. The obtained answers are coded as features, which are used to predict standardized psychiatric measures of depression (PHQ-8) and PTSD (PCL-C), using a Random Forest regressor. Our approach is shown to enhance diagnostic accuracy compared to multiple baselines. It thus establishes a novel framework for interpreting unstructured psychological interviews, bridging the gap between narrative-driven and data-driven approaches for mental health assessment.