China

While document summarization with LLMs has enhanced access to textual information, concerns about the factual accuracy of these summaries persist (e.g., hallucination), especially in the medical domain. Identifying citations from which summaries are derived enables users to assess their accuracy, thereby alleviating this concern. In this paper, we introduce TracSum, a novel benchmark for traceable, aspect-based summarization, in which generated summaries are paired with sentence-level citations, enabling users to trace back to the original context. First, we annotate 500 medical abstracts for seven key medical aspects, yielding 3.5K summary-citations pairs. We then propose a fine-grained evaluation framework for this new task, designed to assess the completeness and consistency of generated content using four metrics. Finally, we introduce a summarization pipeline, Track-Then-Sum, which serves as a baseline method for comparison. In experiments, we evaluate both this baseline and a set of LLMs on TracSum, and conduct a human evaluation to assess the evaluation results. The findings demonstrate that TracSum can serve as an effective benchmark for traceable, aspect-based summarization tasks. We also observe that explicitly performing sentence-level tracking prior to summarization enhances generation accuracy, while incorporating the full context further improves summary completeness. The visualized dataset is anonymously available at https://www.tracsum.info/.

EMNLP 2025

TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domain

resources and evaluation

language modeling

summarization

generation

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

poster

## 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*

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

Word Sense Disambiguation (WSD) aims to determine the correct meaning of a word in context from a predefined inventory, and remains a fundamental challenge in natural language understanding. Existing methods rely heavily on manually annotated data, which limits coverage and generalization. In this work, we propose a scalable framework that leverages large language models (LLMs) as knowledge distillers to construct silver-standard WSD corpora. We explore generation-based distillation, where diverse examples are synthesized for dictionary senses, and annotation-based distillation, where LLMs assign sense labels to polysemous words within real-world corpus sentences. The resulting data is used to train tiny models. Extensive experiments show that models distilled from LLM-generated data outperform those trained on gold-standard corpora, especially on general-domain benchmarks. Our annotation-based model, after balancing sense distribution, achieves 50% F1 gain on the most challenging test set and the best distilled model can match or even exceed the performance of its LLM teacher, despite having over 1000 times fewer parameters. These results demonstrate the effectiveness of LLM-based distillation for building accurate, generalizable, and efficient WSD systems.

Towards General-Domain Word Sense Disambiguation: Distilling Large Language Model into Compact Disambiguator

Activation sparsity provides a dynamic, input-dependent alternative to weight pruning for accelerating inference in large language models (LLMs), effectively reducing unnecessary computations and memory accesses during the forward pass. Despite its promise, existing activation sparsification methods suffer from two major limitations: (1) solely relying on activation magnitude for sparsification, ignoring the coupling influence with the corresponding weights, (2) applying uniform sparsity rates across all blocks without considering block-wise sparsity sensitivity. To address these issues, this paper proposes a novel training-free weight-aware activation sparsity framework, called **WAS**. Firstly, with analyzing the coupling relationshape between weight and activation, we introduce a weight-aware scoring method to measure the activation importance in sparsification. Then, a novel constrained Bayesian optimization algorithm is further devised to set a suitable sparsity ratio for all blocks based on the sparsity sensitivity. Finally, we implement a custom GPU sparsity kernel to support the resulting sparsity patterns for wall-clock decoding speed-ups. Our **WAS** achieves competitive performance at 60% model-level sparsity and significantly outperforms prior methods at higher sparsity levels, achieving up to 1.68× inference speed-up—at no retraining or weight update. Codes are available at https://anonymous.4open.science/r/WAS

Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models

We introduce DRISHTIKON, a first-of-its-kind multimodal and multilingual benchmark centered exclusively on Indian culture, designed to evaluate the cultural understanding of generative AI systems. Unlike existing benchmarks with a generic or global scope, DRISHTIKON offers deep, fine-grained coverage across India’s diverse regions, spanning 15 languages, covering all states and union territories, and incorporating over 64,000 aligned text-image pairs. The dataset captures rich cultural themes including festivals, attire, cuisines, art forms, and historical heritage amongst many more. We evaluate a wide range of vision-language models (VLMs), including open-source small and large models, proprietary systems, reasoning-specialized VLMs, and Indic-focused models—across zero-shot and chain-of-thought settings. Our results expose key limitations in current models’ ability to reason over culturally grounded, multimodal inputs, particularly for low-resource languages and less-documented traditions. DRISHTIKON fills a vital gap in inclusive AI research, offering a robust testbed to advance culturally aware, multimodally competent language technologies.

DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture

Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the trustworthiness of these summaries. Whereas previous work has focused on evidence citation with fixed levels of granularity (e.g. sentence, paragraph, document, etc.), we propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case. We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle". To help models perform this task, we create the Summaries with Unstructured Evidence Text dataset (SUnsET), a synthetic dataset generated using a novel pipeline, which can be used as training supervision for unstructured evidence summarization. We demonstrate across 5 LLMs and 4 datasets spanning human written, synthetic, single, and multi-document settings that LLMs adapted with SUnsET generate more relevant and factually consistent evidence with their summaries, extract evidence from more diverse locations in their context, and can generate more relevant and consistent summaries than baselines with no fine-tuning and fixed granularity evidence. We release SUnsET and our generation code to the public (https://anonymous.4open.science/r/sunset-BD72/README.md).

Unstructured Evidence Attribution for Long Context Query Focused Summarization

This paper focuses on Dialogue Aspect-based Sentiment Quadruple (DiaASQ) analysis, aiming to extract structured quadruples from multi-turn conversations. Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure. To tackle these issues, we propose a novel LLM-based multi-task approach, named textbfTask-textbfaware textbfContrastive textbfMixture textbfof textbfExperts (textbfTaCoMoE), to tackle the DiaASQ task by integrating expert-level contrastive loss within task-oriented mixture of experts layer. TaCoMoE minimizes the distance between the representations of the same expert in the semantic space while maximizing the distance between the representations of different experts to efficiently learn representations of different task samples. Additionally, we design a Graph-Centric Dialogue Structuring strategy for representing dialogue reply structure and perform non-opinion utterances detection to enhance the performance of quadruple extraction. Extensive experiments are conducted on the DiaASQ dataset, demonstrating that our method significantly outperforms existing parameter-efficient fine-tuning techniques in terms of both accuracy and computational efficiency. The code is available at https://anonymous.4open.science/r/TaCoMoE-08B4.

Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detection

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. Grounded on this, we propose **Le**arning to **T**hink-and-**S**earch (**LeTS**), a novel framework that hybridizes stepwise process reward and outcome-based reward to current RL methods for RAG. Extensive experiments demonstrate the generalization and inference efficiency of **LeTS** across various RAG benchmarks. In addition, these results reveal the potential of process- and outcome-level reward hybridization in boosting LLMs' reasoning ability via RL under other scenarios.

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Large language models demonstrate strong problem-solving abilities through reasoning techniques such as chain-of-thought prompting and reflection. However, it remains unclear whether these reasoning capabilities extend to a form of social intelligence: making effective decisions in cooperative contexts. We examine this question using economic games that simulate social dilemmas. First, we apply chain-of-thought and reflection prompting to GPT-4o in a Public Goods Game. We then evaluate multiple off-the-shelf models across six cooperation and punishment games, comparing those with and without explicit reasoning mechanisms. We find that reasoning models consistently reduce cooperation and norm enforcement, favoring individual rationality. In repeated interactions, groups with more reasoning agents exhibit lower collective gains. These behaviors mirror human patterns of "spontaneous giving and calculated greed." Our findings underscore the need for LLM architectures that incorporate social intelligence alongside reasoning, to help address—rather than reinforce—the challenges of collective action.

Spontaneous Giving and Calculated Greed in Language Models

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs’ unethical output and their capability of detecting toxicity have primarily been tested on language data that do not demand complex meaning inference, such as the biased associations of ‘he’ with programmer and ‘she’ with household. Nowadays toxic language adopts a much more creative range of implicit forms, thanks to advanced censorship. In this study, we collect authentic toxic interactions that evade online censorship and that are verified by human annotators as inference-intensive. To evaluate and improve LLMs' reasoning of the authentic implicit toxic language, we propose a new prompting method, Pragmatic Inference Chain (PIC), drawn on interdisciplinary findings from cognitive science and linguistics. The PIC prompting significantly improves the success rate of GPT-4o, Llama-3.1-70B-Instruct, DeepSeek-v2.5, and DeepSeek-v3 in identifying implicit toxic language, compared to five baseline prompts, such as CoT and rule-based baselines. In addition, it also facilitates the models to produce more explicit and coherent reasoning processes, hence can potentially be generalized to other inference-intensive tasks, e.g., understanding humour and metaphors.

Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language

Stance detection aims to identify the viewpoint (favor, against, or neutral) expressed in text towards a specific target. Recent studies on zero-shot and few-shot stance detection focus primarily on learning generalized representations from explicit targets. However, these methods often neglect **implicit yet semantically important targets** and fail to sufficiently **exploit fine-grained contextual cues**, limiting model performance in nuanced scenarios. To overcome these limitations, we propose a novel two-stage framework: First, a data augmentation framework named **Hierarchical Collaborative Target Augmentation** (HCTA) employs Large Language Models (LLMs) to identify and annotate implicit targets via Chain-of-Thought (CoT) prompting and multi-model voting, significantly enriching training data with latent semantic relations. Second, we introduce **FiCAN, a Fine-grained Context-aware Attention Network**, integrating a joint text-target encoding and a sparse cross-attention mechanism to selectively capture critical fine-grained contextual clues. Experiments on the VAST benchmark dataset demonstrate that our approach achieves state-of-the-art results, confirming the effectiveness of implicit target augmentation and fine-grained contextual modeling.

Downloads

Next from EMNLP 2025

Towards General-Domain Word Sense Disambiguation: Distilling Large Language Model into Compact Disambiguator

Similar lecture

OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization