United States

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation, specifically to improving faithfulness through refinement, i.e., revising model-generated outputs to remove factual inconsistencies. We investigate how iterative collaboration among multiple instances and types of large language models (LLMs) enhances subtasks in the refinement process, such as error detection, critiquing unfaithful sentences, and making corrections based on critiques. We design intrinsic evaluations for each subtask, with our findings indicating that both multi-agent (multiple instances) and multi-model (diverse LLM types) approaches benefit error detection and critiquing. Additionally, reframing critiquing and refinement as reranking rather than generation tasks improves multi-agent performance. We consolidate these insights into a final &#39;&#39;recipe&#39;&#39; called **M**ulti-**A**gent **M**ulti-**M**odel **Refine**ment (MAMM-Refine), where multi-agent and multi-model collaboration significantly boosts performance on three summarization datasets as well as on long-form question answering, demonstrating the effectiveness and generalizability of our recipe. Our code is publicly available.

NAACL 2025

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration

long-form qa

query-focused summarization

refinement

multi-agent

factuality

## 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.

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation, specifically to improving faithfulness through refinement, i.e., revising model-generated outputs to remove factual inconsistencies. We investigate how iterative collaboration among multiple instances and types of large language models (LLMs) enhances subtasks in the refinement process, such as error detection, critiquing unfaithful sentences, and making corrections based on critiques. We design intrinsic evaluations for each subtask, with our findings indicating that both multi-agent (multiple instances) and multi-model (diverse LLM types) approaches benefit error detection and critiquing. Additionally, reframing critiquing and refinement as reranking rather than generation tasks improves multi-agent performance. We consolidate these insights into a final ''recipe'' called **M**ulti-**A**gent **M**ulti-**M**odel **Refine**ment (MAMM-Refine), where multi-agent and multi-model collaboration significantly boosts performance on three summarization datasets as well as on long-form question answering, demonstrating the effectiveness and generalizability of our recipe. Our code is publicly available.

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

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures, virtually none of them allow users to provide detailed instructions alongside queries, thus limiting their ability to satisfy complex information needs. In this work, we study the use of instructions in IR systems. First, we introduce our dataset FollowIR, which contains a rigorous instruction evaluation benchmark as well as a training set for helping IR models learn to better follow real-world instructions. FollowIR repurposes detailed instructions -- also known as narratives -- developed for professional assessors to evaluate retrieval systems. In particular, we build our benchmark from three collections curated for shared tasks at the Text REtrieval Conference (TREC). These collections contains hundreds to thousands of labeled documents per query, making them suitable for our exploration. Through this process, we can measure how well IR models follow instructions, through a new pairwise evaluation framework. Our results indicate that existing retrieval models fail to correctly use instructions, using them for basic keywords and struggling to understand long-form information. However, we show that it is possible for IR models to learn to follow complex instructions: our new FollowIR-7B model has significant improvements after fine-tuning on our training set.

FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions

Summarizing movie screenplays presents a unique set of challenges compared to standard document summarization. Screenplays are not only lengthy, but also feature a complex interplay of characters, dialogues, and scenes, with numerous direct and subtle relationships and contextual nuances that are difficult for machine learning models to accurately capture and comprehend. Recent attempts at screenplay summarization focus on fine-tuning transformer-based pre-trained models, but these models often fall short in capturing long-term dependencies and latent relationships, and frequently encounter the ''lost in the middle'' issue. To address these challenges, we introduce DiscoGraMS, a novel resource that represents movie scripts as a movie character-aware discourse graph (CaD Graph). This approach is well-suited for various downstream tasks, such as summarization, question-answering, and salience detection. The model aims to preserve all salient information, offering a more comprehensive and faithful representation of the screenplay's content. We further explore a baseline method that combines the CaD Graph with the corresponding movie script through a late fusion of graph and text modalities, and we present very initial promising results. We have made our code and dataset publicly available.

DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph

Open-vocabulary Extreme Multi-label Classification (OXMC) extends traditional XMC by allowing prediction beyond an extremely large, predefined label set (typically 103
to 1012 labels), addressing the dynamic nature of real-world labeling tasks. However, self-selection bias in data annotation leads to significant missing labels in both training and test data, particularly for less popular inputs. This creates two critical challenges: generation models learn to be “lazy” by under-generating labels, and evaluation becomes unreliable due to insufficient annotation in the test set. In this work, we introduce Positive-Unlabeled Sequence Learning (PUSL), which reframes OXMC as an infinite keyphrase generation task, addressing the generation model’s laziness. Additionally, we propose a suite of evaluation metrics, F1@O and BudgetAccuracy@K, to reliably assess OXMC models with incomplete ground truths. In a highly skewed e-commerce dataset, PUSL generates 30% more unique labels, and 72% of its predictions align with actual user queries. On the less skewed EURLex-4.3k dataset, PUSL demonstrates superior F1 scores, especially as label counts increase from 15 to 30. Our approach effectively tackles both the modeling and evaluation challenges in OXMC with missing labels. Our data split was released in huggingface datasets https://huggingface.co/datasets/windchimeran/pusl

From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning

Biomedical Named Entity Recognition (BioNER) faces significant challenges in real-world applications due to limited annotated data and the constant emergence of new entity types, making zero-shot learning capabilities crucial. While Large Language Models (LLMs) possess extensive domain knowledge necessary for specialized fields like biomedicine, their computational costs often make them impractical. To address these challenges, we introduce OpenBioNER, a lightweight BERT-based cross-encoder architecture that can identify any biomedical entity using only its description, eliminating the need for retraining on new, unseen entity types. Through comprehensive evaluation on established biomedical benchmarks, we demonstrate that OpenBioNER surpasses state-of-the-art baselines, including specialized 7B NER LLMs and GPT-4o, achieving up to 10% higher F1 scores while using 110M parameters only. Moreover, OpenBioNER outperforms existing small-scale models that match textual spans with entity types rather than descriptions, both in terms of accuracy and computational efficiency.

OpenBioNER: Lightweight Open-Domain Biomedical Named Entity Recognition Through Entity Type Description

Entity Linking in biomedical literature is a critical task that enhances the extraction and integration of information from diverse scientific literature. This paper introduces "BioEL", a robust open-source Python package developed to advance Biomedical Entity Linking. BioEL serves as an accessible and comprehensive tool aimed at researchers and practitioners, facilitating the implementation and comparison of BioEL tasks. The package encompasses four key components: (1) Ontology
Object, which manages and applies ontologies across datasets; (2) Dataset Object, integrated with BigBIO for handling annotated corpora; (3) BioEL Model Object, supporting training of various BioEL models, including those with pre-trained weights; and (4) Evaluation Framework, offering robust metrics and methodologies for assessing model performance. The library is extensible and configurable, fostering ongoing development and customization opportunities. This paper details the design principles, core components, and functionalities, and presents benchmarking results on entity-linking tasks using prevalent biomedical datasets.
Our unified evaluation framework and all included models are on
GitHub at https://github.com/pathologydynamics/biomedical-entity-linking.

BioEL: A Comprehensive Python Package for Biomedical Entity Linking

This paper introduces CaseSumm, a novel dataset for long-context summarization in the legal domain that addresses the need for longer and more complex datasets for summarization evaluation. We collect 25.6K U.S. Supreme Court (SCOTUS) opinions and their official summaries, known as ''syllabuses.'' Our dataset is the largest open legal case summarization dataset, and is the first to include summaries of SCOTUS decisions dating back to 1815. We also present a comprehensive evaluation of LLM-generated summaries using both automatic metrics and expert human evaluation, revealing discrepancies between these assessment methods. Our evaluation shows Mistral 7b, a smaller open-source model, outperforms larger models on most automatic metrics and successfully generates syllabus-like summaries. In contrast, human expert annotators indicate that Mistral summaries contain hallucinations. The annotators consistently rank GPT-4 summaries as clearer and exhibiting greater sensitivity and specificity. We find that LLM-based evaluations are not more correlated with human evaluations than traditional automatic metrics. Furthermore, our analysis identifies specific hallucinations in generated summaries, including precedent citation errors and misrepresentations of case facts. These findings demonstrate the limitations of current automatic evaluation methods for legal summarization and highlight the critical role of human evaluation in assessing summary quality, particularly in complex, high-stakes domains.

CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions

Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growing adoption, the actual benefits over simpler fixed-size chunking, where documents are split into consecutive, fixed-size segments, remain unclear. This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks: document retrieval, evidence retrieval, and retrieval-based answer generation. The results show that the computational costs associated with semantic chunking are not justified by consistent performance gains. These findings challenge the previous assumptions about semantic chunking and highlight the need for more efficient chunking strategies in RAG systems.

Is Semantic Chunking Worth the Computational Cost?

Most research on abstractive summarization focuses on single-domain applications, often neglecting how domain shifts between documents affect performance and the generalization ability of summarization models. To address this issue, we introduce DomainSum, a hierarchical benchmark designed to capture fine-grained domain shifts in abstractive summarization. We categorize these shifts into three levels: genre, style, and topic, and demonstrate through comprehensive benchmark analysis that they follow a hierarchical structure. Furthermore, we evaluate the domain generalization capabilities of commonly used pre-trained language models (PLMs) and large language models (LLMs) in both in-domain and cross-domain settings. Our benchmark and source code are released at https://github.com/hpzhang94/DomainSum.

DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization

Distantly Supervised Named Entity Recognition (DS-NER) has attracted attention due to its scalability and ability to automatically generate labeled data. However, distant annotation introduces many mislabeled instances, limiting its performance. Most of the existing work attempt to solve this problem by developing intricate models to learn from the noisy labels. An alternative approach is to attempt to clean the labeled data, thus increasing the quality of distant labels. This approach has received little attention for NER. In this paper, we propose a training dynamics-based label cleaning approach, which leverages the behavior of a model as training progresses to characterize the distantly annotated samples. We also introduce an automatic threshold estimation strategy to locate the errors in distant labels. Extensive experimental results demonstrate that: (1) models trained on our cleaned DS-NER datasets, which were refined by directly removing identified erroneous annotations, achieve significant improvements in F1-score, ranging from 3.18% to 8.95%; and (2) our method outperforms numerous advanced DS-NER approaches across four datasets.

DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many applications, especially when further fine-tuning is required. To address these limitations, smaller models are typically preferred for deployment. However, their training is hindered by the scarcity of labeled data. In contrast, unlabeled data is often readily which can be leveraged by using LLMs to generate pseudo-labels for training smaller models. This enables the smaller models (student) to acquire knowledge from LLMs (teacher) while reducing computational costs. This process introduces challenges, such as potential noisy pseudo-labels. % and the high computational expense of processing large unlabeled datasets. Selecting high-quality and informative data is therefore critical to enhance model performance while improving the efficiency of data utilization. To address this, we propose LLKD that enables Learning with Less computational resources and less data for Knowledge Distillation from LLMs. LLKD is an adaptive sample selection method that incorporates signals from both the teacher and student. Specifically, it prioritizes samples where the teacher demonstrates high confidence in its labeling, indicating reliable labels, and where the student exhibits a high information need, identifying challenging samples that require further learning. Our comprehensive experiments show that LLKD achieves superior performance across various datasets with higher data efficiency.

Downloads

Next from NAACL 2025

FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions

Similar lecture

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