United States

Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-linguistic reward signals, we introduce Learning through Communication (LTC). We design a universal buffer to store all the feedback, and an iterative pipeline to enable an LLM agent to explore and update its policy in an given environment. To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-agent environments. We evaluate the efficacy of our LTC approach on four diverse datasets: ALFWorld (single-agent), HotpotQA (multi-agent collaboration), Chameleon (multi-agent competition), and GSM8k (multi-agent teacher-student). On these data sets, LTC outperforms the supervised instruction fine-tuning baselines by 3.6% to 12%. These results highlight the versatility and efficiency of LTC in facilitating online adaptation for LLM agents.

NAACL 2025

Adapting LLM Agents with Universal Communication Feedback

agent

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

poster

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Multi-agent systems, which consist of multiple AI models interacting within a shared environment, are increasingly used for persona-based interactions. However, if not carefully designed, these systems can reinforce implicit biases in large language models (LLMs), raising concerns about fairness and equitable representation. We present MALIBU, a novel benchmark developed to assess the degree to which LLM-based multi-agent systems implicitly reinforce social biases and stereotypes. MALIBU evaluates bias in LLM-based multi-agent systems through scenario-based assessments. AI models complete tasks within predefined contexts, and their responses undergo evaluation by an LLM-based multi-agent judging system in two phases. In the first phase, judges score responses labeled with specific demographic personas (e.g., gender, race, religion) across four metrics. In the second phase, judges compare paired responses assigned to different personas, scoring them and selecting the superior response. Our study quantifies biases in LLM-generated outputs, revealing that bias mitigation may favor marginalized personas over true neutrality, emphasizing the need for nuanced detection, balanced fairness strategies, and transparent evaluation benchmarks in multi-agent systems.

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered

Transformer architectures have become the backbone of domains such as language modeling but often suffer in many inference settings due to their quadratic self-attention. Recently proposed subquadratic architectures, such as State Space Models (SSMs), reveal promising results ranging from more efficient compute to outperforming transformer-based models on certain benchmarks. Theory of Mind (ToM)--the ability to reason about one’s own and other’s mental states--is a complex task that poses significant challenges to state-of-the-art models. While previous works have focused on ToM reasoning solely in transformer-based models, we evaluate a leading transformer-based model and a leading SSM on various long context ToM tasks. Through our evaluation, we reveal that although the SSM generally performs worse on ToM tasks compared to the transformer-based model, the SSM exhibits less performance degradation on more difficult tasks, indicating potential advantages for SSMs in difficult and long-context ToM reasoning.

DIG-DIS: Transformer-Based Models vs State Space Models on Complex Theory of Mind Reasoning Tasks

Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval methods typically divide reference documents into passages, treating them in isolation. These passages, however, are often interrelated, such as passages that are contiguous or share the same keywords. Therefore, it is crucial to recognize such relatedness for enhancing the retrieval process. In this paper, we propose a novel retrieval method, called GNN-Ret, which leverages graph neural networks (GNNs) to enhance retrieval by exploiting the relatedness between passages. Specifically, we first construct a graph of passages by connecting passages that are structure-related or keyword-related. A graph neural network (GNN) is then leveraged to exploit the relationships between passages and improve the retrieval of supporting passages. Furthermore, we extend our method to handle multi-hop reasoning questions using a recurrent graph neural network (RGNN), named RGNN-Ret. At each step, RGNN-Ret integrates the graphs of passages from previous steps, thereby enhancing the retrieval of supporting passages. Extensive experiments on benchmark datasets demonstrate that GNN-Ret achieves higher accuracy for question answering with a single query of LLMs than strong baselines that require multiple queries, and RGNN-Ret further improves accuracy and achieves state-of-the-art performance, with up to 10.4 accuracy improvement on the 2WikiMQA dataset.

Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models

Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. However, Multi-hop Question Answering (MHQA) remains challenging for many existing models due to issues like hallucination, error propagation, and limited context length. To address these challenges and enhance LLMs' performance on MHQA, we propose the Self-Guiding prompting Finite State Machine (SG-FSM), designed to strengthen multi-hop reasoning abilities. Unlike traditional chain-of-thought methods, SG-FSM tackles MHQA by iteratively breaking down complex questions into sub-questions, correcting itself to improve accuracy. It processes one sub-question at a time, dynamically deciding the next step based on the current context and results, functioning much like an automaton. Experiments across various benchmarks demonstrate the effectiveness of our approach, outperforming strong baselines on challenging datasets such as Musique. SG-FSM reduces hallucination, enabling recovery of the correct final answer despite intermediate errors. It also improves adherence to specified output formats, simplifying evaluation significantly.

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine

Existing multimodal summarization approaches struggle with scenarios involving numerous images as input, leading to a heavy load for readers. Summarizing both the input text and numerous images helps readers quickly grasp the key points of multimodal input. This paper introduces a novel task, Numerous Images-Oriented Multimodal Summarization (NIMMS). To benchmark this task, we first construct the dataset based on a public multimodal summarization dataset. Considering that most existing metrics evaluate summaries from a unimodal perspective, we propose a new Multimodal Information evaluation (M-info) method, measuring the differences between the generated summary and the multimodal input. Finally, we compare various summarization methods on NIMMS and analyze associated challenges. Experimental results have shown that M-info correlates more closely with human judgments than five widely used metrics. Meanwhile, existing models struggle with summarizing numerous images. We hope that this research will shed light on the development of multimodal summarization. Furthermore, our code and dataset will be released to the public.

Pay More Attention to Images: Numerous Images-Oriented Multimodal Summarization

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with a detailed analysis aimed at disentangling risks through step-by-step reasoning within multimodal inputs. We find that systematic multimodal risk disentanglement substantially enhances the risk awareness of MLLMs. Via leveraging the strong discriminative abilities of multimodal risk disentanglement, we further introduce **DREAM** (***D**isentangling **R**isks to **E**nhance Safety **A**lignment in **M**LLMs*), a novel approach that enhances safety alignment in MLLMs through supervised fine-tuning and iterative Reinforcement Learning from AI Feedback (RLAIF). Experimental results show that DREAM significantly boosts safety during both inference and training phases without compromising performance on normal tasks (namely oversafety), achieving a 16.17% improvement in the SIUO safe&effective score compared to GPT-4V.

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models

Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples, reducing the cost of SC with minimal impact on performance. Both methods, however, do not exploit the prior information about question difficulty. It often results in unnecessary repeated sampling for easy questions that could be accurately answered with just one attempt, wasting resources. To tackle this problem, we propose Difficulty-Adaptive Self-Consistency (DSC), which leverages the difficulty information of batch queries from both prior and posterior perspectives to adaptively allocate inference resources, further reducing the overall cost of SC. To demonstrate the effectiveness of DSC, we conduct extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning on six benchmarks. The empirical results show that DSC consistently surpasses the strong baseline ASC and ESC in terms of costs by a significant margin, while attaining comparable performances.

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning

The rise of Large Language Models (LLMs) revolutionizes information retrieval, allowing users to obtain required answers through complex instructions within conversations. However, publicly available services remain inadequate in addressing the needs of faculty and students to search campus-speciﬁc information. It is primarily due to the LLM’s lack of domain-speciﬁc knowledge and the limitation of search engines in supporting multilingual and timely scenarios. To tackle these challenges, we introduce ALOHA, a multilingual agent enhanced by hierarchical retrieval for university orientation. We also integrate external APIs into the front-end interface to provide interactive service. The human evaluation and case study show our proposed system has strong capabilities to yield correct, timely, and user-friendly responses to the queries in multiple languages, surpassing commercial chatbots and search engines. The system has been deployed and has provided service for more than 12,000 people.

ALOHA: Empowering Multilingual Agent for University Orientation with Hierarchical Retrieval

Generated texts from large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. These findings motivate research efforts aiming to understand and measure such effects. This paper introduces a causal formulation for bias measurement in generative language models. Based on this theoretical foundation, we outline a list of desiderata for designing robust bias benchmarks. We then propose a benchmark called OccuGender, with a bias-measuring procedure to investigate occupational gender bias. We test several state-of-the-art open-source LLMs on OccuGender, including Llama, Mistral, and their instruction-tuned versions. The results show that these models exhibit substantial occupational gender bias. Lastly, we discuss prompting strategies for bias mitigation and an extension of our causal formulation to illustrate the generalizability of our framework.

Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias

Large language models (LLM) have shown remarkable abilities in text generation, question answering, language translation, reasoning and many other tasks. It continues to advance rapidly and is becoming increasingly influential in various fields, from technology and business to education and entertainment. Despite LLM's success in multiple areas, its ability to play abstract games, such as chess, is underexplored. Chess-playing requires the language models to output legal and reasonable moves from textual inputs. Here, we propose the Large language model ChessLLM to play full chess games. We transform the game into a textual format with the best move represented in the Forsyth-Edwards Notation. We show that by simply supervised fine-tuning, our model has achieved a professional-level Elo rating of 1788 in matches against the standard Elo-rated Stockfish when permitted to sample 10 times. We further show that data quality is important. Long-round data supervision enjoys a 350 Elo rating improvement over short-round data.

Downloads

Next from NAACL 2025

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered

Similar lecture

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES