NAACL 2025 论文列表

Understanding user satisfaction with conversational systems, known as User Satisfaction Estimation (USE), is essential for assessing dialogue quality and enhancing user experiences. However, existing methods for USE face challenges due to limited understanding of underlying reasons for user dissatisfaction and the high costs of annotating user intentions. To address these challenges, we propose PRAISE (Plan and Retrieval Alignment for Interpretable Satisfaction Estimation), an interpretable framework for effective user satisfaction prediction. PRAISE operates through three key modules. The Strategy Planner develops strategies, which are natural language criteria for classifying user satisfaction. The Feature Retriever then incorporates knowledge on user satisfaction from Large Language Models (LLMs) and retrieves relevance features from utterances. Finally, the Score Analyzer evaluates strategy predictions and classifies user satisfaction. Experimental results demonstrate that PRAISE achieves state-of-the-art performance on three benchmarks for the USE task. Beyond its superior performance, PRAISE offers additional benefits. It enhances interpretability by providing instance-level explanations through effective alignment of utterances with strategies. Moreover, PRAISE operates more efficiently than existing approaches by eliminating the need for LLMs during the inference phase.

The Bourne-Again Shell (Bash) command-line interface for Linux systems has complex syntax and requires extensive specialized knowledge. Using the natural language to Bash command (NL2SH) translation capabilities of large language models (LLMs) for command composition circumvents these issues. However, the NL2SH performance of LLMs is difficult to assess due to inaccurate test data and unreliable heuristics for determining the functional equivalence of Bash commands. We present a manually verified test dataset of 600 instruction-command pairs and a training dataset of 40,939 pairs, increasing the size of previous datasets by 441% and 135%, respectively. Further, we present a novel functional equivalence heuristic that combines command execution with LLM evaluation of command outputs. Our heuristic can determine the functional equivalence of two Bash commands with 95% confidence, a 16% increase over previous heuristics. Evaluation of popular LLMs using our test dataset and heuristic demonstrates that parsing, in-context learning, in-weight learning and constrained decoding can improve NL2SH accuracy by up to 32%. Our findings emphasize the importance of dataset quality, execution-based evaluation and translation method for advancing NL2SH translation. Our code is available at https://github.com/westenfelder/NL2SH

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens — especially stopwords, articles, and commas — consistently degrades performance on MMLU and BABILong-4k, even if removing only irrelevant tokens. Our analysis also shows a strong correlation between contextualization and linearity, where linearity measures how closely the transformation from one layer’s embeddings to the next can be approximated by a single linear mapping. These findings underscore the hidden importance of “filler” tokens in maintaining context. For further exploration, we present LLM-Microscope, an open-source toolkit that assesses token-level nonlinearity, evaluates contextual memory, visualizes intermediate layer contributions (via an adapted Logit Lens), and measures the intrinsic dimensionality of representations. This toolkit illuminates how seemingly trivial tokens can be critical for long-range understanding.

Conversations often adhere to well-understood social norms that vary across cultures. For example, while addressing parents by name is commonplace in the West, it is rare in most Asian cultures. Adherence or violation of such norms often dictates the tenor of conversations. Humans are able to navigate social situations requiring cultural awareness quite adeptly. However, it is a hard task for NLP models.In this paper, we tackle this problem by introducing a Cultural Context Schema for conversations. It comprises (1) conversational information such as emotions, dialogue acts, etc., and (2) cultural information such as social norms, violations, etc. We generate ~110k social norm and violation descriptions for ~23k conversations from Chinese culture using LLMs. We refine them using automated verification strategies which are evaluated against culturally aware human judgements. We organize these descriptions into meaningful structures we call Norm Concepts, using an interactive human-in-loop framework. We ground the norm concepts and the descriptions in conversations using symbolic annotation. Finally, we use the obtained dataset for downstream tasks such as emotion, sentiment, and dialogue act detection. We show that it significantly improves the empirical performance.

Automatically generated passwords and passphrases are a cornerstone of IT security. Yet, these passphrases are often hard to remember and see only limited adoption. In this work, we use large language models to generate passphrases with rigorous security guarantees via the computation of the entropy of the output as a metric of the security of the passphrase. We then present a range of practical methods to generate language model outputs with sufficient entropy: raising entropy through in-context examples and generation through a new top-q truncation method. We further verify the influence of prompt construction in steering the output topic and grammatical structure. Finally, we conduct user studies to determine the adoption rates for these LLM-generated passphrases in practice.

Large Language Models (LLMs) have demonstrated emergent common-sense reasoning and Theory of Mind (ToM) capabilities, making them promising candidates for developing coordination agents. This study introduces the LLM-Coordination Benchmark, a novel benchmark for analyzing LLMs in the context of Pure Coordination Settings, where agents must cooperate to maximize gains. Our benchmark evaluates LLMs through two distinct tasks. The first is Agentic Coordination, where LLMs act as proactive participants in four pure coordination games. The second is Coordination Question Answering (CoordQA), which tests LLMs on 198 multiple-choice questions across these games to evaluate three key abilities: Environment Comprehension, ToM Reasoning, and Joint Planning. Results from Agentic Coordination experiments reveal that LLM-Agents excel in multi-agent coordination settings where decision-making primarily relies on environmental variables but face challenges in scenarios requiring active consideration of partners’ beliefs and intentions. The CoordQA experiments further highlight significant room for improvement in LLMs’ Theory of Mind reasoning and joint planning capabilities. Zero-Shot Coordination (ZSC) experiments in the Agentic Coordination setting demonstrate that LLM agents, unlike RL methods, exhibit robustness to unseen partners. These findings indicate the potential of LLMs as Agents in pure coordination setups and underscore areas for improvement.

In multi-agent scenarios, the ability to anticipate and respond to opponents is essential, particularly in environments involving adversarial and collaborative interactions. In this paper, we introduce Explicit Models of Opponents (EMO) based on Large Language Models (LLMs), enabling agents to better predict and adapt to diverse, dynamic multi-agent interactions. Unlike traditional methods that often simplify multi-agent interactions using a single opponent model, EMO constructs an individual model for each opponent and aligns these models working in synergy through a bi-level feedback-refinement framework. We test EMO alongside several reasoning methods in multi-player deduction games, where agents must infer hidden information about their opponents. The results show that EMO significantly enhances agents’ decision-making, outperforming traditional single-model approaches. Our findings demonstrate that EMO can be a powerful tool for enhancing LLM-based agents in complex multi-agent systems.

Interestingly, LLMs yet struggle with some basic tasks that humans find trivial to handle, e.g., counting the number of character r’s in the word “strawberry”. There are several popular conjectures (e.g., tokenization, architecture and training data) regarding the reason for deficiency of LLMs in simple word-based counting problems, sharing the similar belief that such failure stems from model pretraining hence probably inevitable during deployment. In this paper, we carefully design multiple evaluation settings to investigate validity of prevalent conjectures. Meanwhile, we measure transferability of advanced mathematical and coding reasoning capabilities from specialized LLMs to simple counting tasks. Although specialized LLMs suffer from counting problems as well, we find conjectures about inherent deficiency of LLMs invalid and further seek opportunities to elicit knowledge and capabilities from LLMs which are beneficial to counting tasks. Compared with strategies such as finetuning and in-context learning that are commonly adopted to enhance performance on new or challenging tasks, we show that engaging reasoning is the most robust and efficient way to help LLMs better perceive tasks with more accurate responses.We hope our conjecture validation design could provide insights to study future critical failure modes of LLMs. Based on challenges in transferring advanced capabilities to much simpler tasks, we call for more attention to model capability acquisition and evaluation. We also highlight the importance of cultivating consciousness of “reasoning before responding” during model pretraining.

This paper analyzes the safety of Large Language Models (LLMs) in interactions with children below age of 18 years. Despite the transformative applications of LLMs in various aspects of children’s lives, such as education and therapy, there remains a significant gap in understanding and mitigating potential content harms specific to this demographic. The study acknowledges the diverse nature of children, often overlooked by standard safety evaluations, and proposes a comprehensive approach to evaluating LLM safety specifically for children. We list down potential risks that children may encounter when using LLM-powered applications. Additionally, we develop Child User Models that reflect the varied personalities and interests of children, informed by literature in child care and psychology. These user models aim to bridge the existing gap in child safety literature across various fields. We utilize Child User Models to evaluate the safety of six state-of-the-art LLMs. Our observations reveal significant safety gaps in LLMs, particularly in categories harmful to children but not adults.

This paper introduces an LLM-based Latin-to-English translation platform designed to address the challenges of translating Latin texts. We named the model LITERA, which stands for Latin Interpretation and Translations into English for Research Assistance. Through a multi-layered translation process utilizing a fine-tuned version of GPT-4o-mini and GPT-4o, LITERA offers an unprecedented level of accuracy, showcased by greatly improved BLEU scores, particularly in classical Latin, along with improved BLEURT scores. The development of LITERA involved close collaboration with Duke University’s Classical Studies Department, which was instrumental in creating a small, high-quality parallel Latin-English dataset. This paper details the architecture, fine-tuning methodology, and prompting strategies used in LITERA, emphasizing its ability to produce literal translations.

While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model’s length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM’s ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.

Large Language Models (LLMs) have great success in natural language processing tasks such as response generation. However, their use in tabular data has been limited due to their inferior performance compared to traditional machine learning models (TMLs) such as XGBoost. We find that the pre-trained knowledge of LLMs enables them to interpret new variables that appear in a test without additional training, a capability central to the concept of Out-of-Variable (OOV). From the findings, we propose a Language-Based-Classifier (LBC), a classifier that maximizes the benefits of LLMs to outperform TMLs on OOV tasks. LBC employs three key methodological strategies: 1) Categorical changes to adjust data to better fit the model’s understanding, 2) Advanced order and indicator to enhance data representation to the model, and 3) Using verbalizer to map logit scores to classes during inference to generate model predictions. These strategies, combined with the pre-trained knowledge of LBC, emphasize the model’s ability to effectively handle OOV tasks. We empirically and theoretically validate the superiority of LBC. LBC is the first study to apply an LLM-based model to OOV tasks. The source code is at https://github.com/ASDASDanonymous/Language-Based-Classifier-forOOVtasks.

Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Yet, these models are not robust in precisely reasoning about physical and spatial configurations of objects, especially when instructed with unconventional, thereby out-of-distribution descriptions, such as “a chair with five legs”. In this paper, we propose a language agent with chain-of-3D-thoughts (L3GO), an inference-time approach that can reason about part-based 3D construction of unconventional objects that current data-driven diffusion models struggle with. More concretely, we use large language models as agents to compose a desired object via trial-and-error within the 3D simulation environment. To facilitate our investigation, we develop a new benchmark, Unconventionally Feasible Objects (UFO), as well as SimpleBlenv, a wrapper environment built on top of Blender where language agents can build and compose atomic building blocks via API calls. Human and automatic GPT-4V evaluations show that our approach surpasses the standard GPT-4 and other language agents (e.g., ReAct and Reflexion) for 3D mesh generation on ShapeNet. Moreover, when tested on our UFO benchmark, our approach outperforms other state-of-the-art text-to-2D image and text-to-3D models based on human evaluation.

Video-based dialogue systems have compelling application value, such as education assistants, thereby garnering growing interest. However, the current video-based dialogue systems are limited by their reliance on a single dialogue type, which hinders their versatility in practical applications across a range of scenarios, including question-answering and emotionally dialog, etc. In this paper, we identify this challenge as how to generate video-driven multilingual mixed-type dialogues. To mitigate this challenge, we propose a novel task and create a human-to-human video-driven multilingual mixed-type dialogue corpus, termed KwaiChat, containing a total of 93,209 videos and 246,080 dialogues, across 4 dialogue types, 30 domains, 4 languages, and 13 topics. Additionally, we establish baseline models on KwaiChat. An extensive analysis of 7 distinct LLMs on KwaiChat reveals that GPT-4o achieves the best performance but still cannot perform well in this situation even with the help of in-context learning and fine-tuning, which indicates that the task is not trivial and needs further research.

Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate query expansions more grounded to document corpus. However, these methods mostly focus on enhancing textual similarities between search queries and target documents, overlooking document relations. For queries like “Find me a highly rated camera for wildlife photography compatible with my Nikon F-Mount lenses”, existing methods may generate expansions that are semantically similar but structurally unrelated to user intents. To handle such semi-structured queries with both textual and relational requirements, in this paper we propose a knowledge-aware query expansion framework, augmenting LLMs with structured document relations from knowledge graph (KG). To further address the limitation of entity-based scoring in existing KG-based methods, we leverage document texts as rich KG node representations and use document-based relation filtering for our Knowledge-Aware Retrieval (KAR). Extensive experiments on three datasets of diverse domains show the advantages of our method compared against state-of-the-art baselines on textual and relational semi-structured retrieval.

Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG2RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specifically, after performing a semantic-based retrieval to provide seed chunks, KG2RAG employs a KG-guided chunk expansion process and a KG-based chunk organization process to deliver relevant and important knowledge in well-organized paragraphs. Extensive experiments conducted on the HotpotQA dataset and its variants demonstrate the advantages of KG2RAG compared to existing RAG-based approaches, in terms of both response quality and retrieval quality.

To deploy language models safely, it is crucial that they abstain from responding to inappropriate requests. Several prior studies test the safety promises of models based on their effectiveness in blocking malicious requests. In this work, we focus on evaluating the underlying techniques that cause models to abstain. We create ‘SELECT‘, a benchmark derived from a set of benign concepts (e.g., “rivers”) from a knowledge graph. Focusing on benign concepts isolates the effect of safety training, and grounding these concepts in a knowledge graph allows us to study the *generalization* and *specificity* of abstention techniques. Using ‘SELECT‘, we benchmark different abstention techniques over six open-weight and closed-source models. We find that the examined techniques indeed cause models to abstain with over 80% abstention rates. However, these techniques are not as effective for descendants of the target concepts, where abstention rates drop by 19%. We also characterize the generalization-specificity trade-offs for different techniques. Overall, no single technique is invariably better than others, and our findings inform practitioners of the various trade-offs involved.

Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inadequacy primarily stems from the lack of built-in action knowledge in language agents, which fails to effectively guide the planning trajectories during task solving and results in planning hallucination. To address this issue, we introduce KnowAgent, a novel approach designed to enhance the planning capabilities of LLMs by incorporating explicit action knowledge. Specifically, KnowAgent employs an action knowledge base and a knowledgeable self-learning strategy to constrain the action path during planning, enabling more reasonable trajectory synthesis, and thereby enhancing the planning performance of language agents. Experimental results on HotpotQA and ALFWorld based on various backbone models demonstrate that KnowAgent can achieve comparable or superior performance to existing baselines. Further analysis indicates the effectiveness of KnowAgent in terms of planning hallucinations mitigation.

The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and robustness.While, existing methods either focus on model generalization or concentrate on robustness.The unified mechanism, to simultaneously address the challenges of generalization and robustness, is less explored. In this paper, we first empirically reveal an intrinsic mechanism for model generalization and robustness of AIGT detection task.Then, we proposed a novel AIGT detection method (DP-Net) via dynamic perturbations introduced by a reinforcement learning with elaborated reward and action.Experimentally, extensive results show that the proposed DP-Net significantly outperforms some state-of-the-art AIGT detection methods for generalization capacity in three cross-domain scenarios.Meanwhile, the DP-Net achieves best robustness under two text adversarial attacks.