China

Recent advances in Relation Extraction (RE) emphasize Zero-Shot methodologies, aiming to recognize unseen relations between entities with no annotated data. Although Large Language Models (LLMs) have demonstrated outstanding performance in many NLP tasks, their performance in Zero-Shot RE (ZSRE) without entity type constraints still lags behind Small Language Models (SLMs). LLM-based ZSRE often involves manual interventions and significant computational overhead, especially when scaling to large-scale multi-choice data. To this end, we introduce RE-GAR-AD, which not only leverages the generative capability of LLMs but also utilizes their representational power without tuning LLMs. We redefine LLM-based ZSRE as a retrieval challenge, utilizing a Generation-Augmented Retrieval framework coupled with a retrieval Adjuster. Specifically, our approach guides LLMs through crafted prompts to distill sentence semantics and enrich relation labels. We encode sentences and relation labels using LLMs and match their embeddings in a triplet fashion. This retrieval technique significantly reduces token input requirements. Additionally, to further optimize embeddings, we propose a plug-in retrieval adjuster with only 2M parameters, which allows rapid fine-tuning without accessing LLMs&#39; parameters. Our LLM-based model demonstrates comparable performance on multiple benchmarks.

EMNLP 2025

Generation-Augmented Retrieval: Rethinking the Role of Large Language Models in Zero-Shot Relation Extraction

zero-shot extraction

relation extraction

## 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."<br>

*Message from the General Chair, Dirk Hovy*





<br>

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

Recent advances in Relation Extraction (RE) emphasize Zero-Shot methodologies, aiming to recognize unseen relations between entities with no annotated data. Although Large Language Models (LLMs) have demonstrated outstanding performance in many NLP tasks, their performance in Zero-Shot RE (ZSRE) without entity type constraints still lags behind Small Language Models (SLMs). LLM-based ZSRE often involves manual interventions and significant computational overhead, especially when scaling to large-scale multi-choice data. To this end, we introduce RE-GAR-AD, which not only leverages the generative capability of LLMs but also utilizes their representational power without tuning LLMs. We redefine LLM-based ZSRE as a retrieval challenge, utilizing a Generation-Augmented Retrieval framework coupled with a retrieval Adjuster. Specifically, our approach guides LLMs through crafted prompts to distill sentence semantics and enrich relation labels. We encode sentences and relation labels using LLMs and match their embeddings in a triplet fashion. This retrieval technique significantly reduces token input requirements. Additionally, to further optimize embeddings, we propose a plug-in retrieval adjuster with only 2M parameters, which allows rapid fine-tuning without accessing LLMs' parameters. Our LLM-based model demonstrates comparable performance on multiple benchmarks.

poster

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour or risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. This work explores how agents trained with imitation learning can learn robust representations from both optimal and suboptimal demonstrations when given access to constructive language feedback as a means to contextualise different modes of behaviour. We directly provide language feedback embeddings as part of the input sequence into a Transformer-based policy, and optionally complement the traditional next action prediction objective with auxiliary self-supervised learning objectives for feedback prediction. We test our approach on a range of embodied Vision-and-Language tasks in our custom BabyAI-XGen environment and show significant improvements in agents' compositional generalisation abilities and robustness, suggesting that our data-efficient method allows models to successfully convert suboptimal behaviour into learning opportunities. Overall, our results suggest that language feedback is a competitive and intuitive alternative to intermediate scalar rewards for language-specified embodied tasks.

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks

Lemmatization is the task of transforming all words in a given text to their dictionary forms. While large language models (LLMs) have demonstrated their ability to achieve competitive results across a wide range of NLP tasks, there is no prior evidence of how effective they are in the contextual lemmatization task. In this paper, we empirically investigate the capacity of the latest generation of LLMs to perform in-context lemmatization, comparing it to the traditional fully supervised approach. In particular, we consider the setting in which supervised training data is not available for a target domain or language, comparing (i) encoder-only supervised approaches, fine-tuned out-of-domain, and (ii) cross-lingual methods, against direct in-context lemma generation with LLMs. Our experimental investigation across 12 languages of different morphological complexity finds that, while encoders remain competitive in out-of-domain settings when fine-tuned on gold data, current LLMs reach state-of-the-art results for most languages by directly generating lemmas in-context without prior fine-tuning, provided just with a few examples. Data and code will be made available upon publication.

Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data

Recent advances in chain-of-thought (CoT) reasoning have improved complex video understanding, but existing methods often struggle to adapt to domain-specific skills (e.g., temporal grounding, event detection, spatial relations) over various video content. To address this, we propose Video-Skill-CoT (aka Video-SKoT) a framework that automatically constructs and leverages skill-aware CoT supervisions for domain-adaptive video reasoning. First, we construct skill-based CoT annotations: We extract domain-relevant reasoning skills from training questions, cluster them into a shared skill taxonomy, and create detailed multi-step CoT rationale tailored to each video question pair for training. Second, we introduce a skill-specific expert learning framework. Each expert module specializes in a subset of reasoning skills and is trained with lightweight adapters using the collected CoT supervision. We demonstrate the effectiveness of the proposed approach on three video understanding benchmarks, where Video-SKoT consistently outperforms strong baselines. We also provide in-depth analyses on comparing different CoT annotation pipelines and learned skills over multiple video domains.

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning

Understanding temporal relations between events in a text is essential for determining its temporal structure. Recent advancements in large language models (LLMs) have spurred research on temporal relation extraction. However, LLMs perform poorly in zero-shot and few-shot settings, often underperforming smaller fine-tuned models. Despite these limitations, little attention has been given to improving LLMs in temporal structure extraction tasks. This study systematically examines LLMs’ ability to extract and infer discourse-level temporal relations, identifying factors influencing their reasoning and extraction capabilities, including input context, reasoning process and ensuring consistency. We propose a three-step framework to improve LLMs' temporal relation extraction capabilities: context selection, prompts inspired by Allen's interval algebra (Allen, 1983), and reflection-based consistency learning (Shinn et al., 2024). Our results show the effectiveness of our method in guiding LLMs towards structured processing of temporal structure in discourse.

Consistent Discourse-level Temporal Relation Extraction Using Large Language Models

Large vision-language models (LVLMs) have shown remarkable performance in visual-language understanding for downstream multimodal tasks. While their capabilities are improving, problems emerge simultaneously. Among those problems, the hallucinations have attracted much attention, which stands for the phenomenon where LVLMs generate contradictory content to their input visual and text contents. Many approaches have been proposed to deal with this issue, such as contrastive decoding and attention manipulation. However, contrastive decoding methods struggle in constructing appropriate contrastive samples, and attention manipulation methods are highly sensitive, lacking stability. In this work, we propose image head Masked Contrastive Decoding (MaskCD). Our approach utilizes the "image heads" in LVLMs, masking them to construct contrastive samples for contrastive decoding. We evaluated MaskCD on LLaVA-1.5-7b and Qwen-VL-7b, using various benchmarks such as CHAIR, POPE, and MME. The results demonstrate that MaskCD effectively alleviates the phenomenon of hallucinations and retains the general capabilities of LVLMs.

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding

Gradient-based data influence approximation has been leveraged to select useful data samples in the supervised fine-tuning of large language models. However, the computation of gradients throughout the fine-tuning process requires too many resources to be feasible in practice. In this paper, we propose an efficient gradient-based data selection framework with clustering and a modified Upper Confidence Bound (UCB) algorithm. Based on the intuition that data samples with similar gradient features will have similar influences, we first perform clustering on the training data pool. Then, we frame the inter-cluster data selection as a constrained computing budget allocation problem and consider it a multi-armed bandit problem. A modified UCB algorithm is leveraged to solve this problem. Specifically, during the iterative sampling process, historical data influence information is recorded to directly estimate the distributions of each cluster, and a cold start is adopted to balance exploration and exploitation. Experimental results on various benchmarks show that our proposed framework, ClusterUCB, can achieve comparable results to the original gradient-based data selection methods while greatly reducing computing consumption.

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs

The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applicability in real-world scenarios. In this paper, we introduce two Korean expert-level benchmarks. KMMLU-Redux, reconstructed from the existing KMMLU consists of questions from the Korean National Technical Qualification exams, with critical errors removed to enhance reliability. KMMLU-Pro is based on Korean National Professional Licensure exams to reflect professional knowledge in Korea. Our experiments demonstrate that these benchmarks comprehensively represent industrial knowledge in Korea.

From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluation

The Impression section of a radiology report summarizes critical findings of a radiology report and thus plays a crucial role in communication between radiologists and physicians. Research on radiology report summarization mostly focuses on generating the Impression section by summarizing information from the Findings section, which typically details the radiologist's observations in the radiology images. Recent work start to explore how to incorporate radiology images as input to multimodal summarization models, with the assumption that it can improve generated summary quality, as it contains richer information. However, the real effectiveness of radiology images remains unclear. To answer this, we conduct a thorough analysis to understand whether current multimodal models can utilize radiology images in summarizing Findings section. Our analysis reveals that current multimodal models often fail to effectively utilize radiology images. For example, masking the image input leads to minimal or no performance drop. Expert annotation study shows that radiology images are unnecessary when they write the Impression section.

The More, The Better? A Critical Study of Multimodal Context in Radiology Report Summarization

Large Language Models (LLMs) excel at reasoning but often struggle with multi-step tasks due to limited contextual understanding. While Retrieval-Augmented Generation (RAG) provides external context, it relies on static datasets and struggles to generalize across diverse queries. In this work, we propose a Generative Retrieval-Aligned Demonstrator (GRAD), a dynamic demonstration-based approach where an LLM model is trained to generate input-specific concise demonstrations. By tailoring demonstrations to each input, our method offers better contextual support than traditional RAG approaches. GRAD is grounded in a generative strategy allowing adaptive prompting without needing external retrieval. We demonstrate the superiority of GRAD under the budget constraints, where we limit both the number of tokens per demonstration and the output response budget. Trained solely on math dataset, GRAD consistently outperforms strong baselines ranging from math reasoning to advanced STEM questions on Qwen2.5-14B. This showcases the robust generalization of GRAD to out-of-distribution (OOD) STEM tasks, such as physics, chemistry and computer science. Since demonstrations can be generated by a different, smaller model, GRAD might reduce training cost while still maintaining similar accuracy. This work introduces a scalable demonstration generator model that is the first step towards a new few-shot learning paradigm in constrained, limited-resource settings.

GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning

In scientific research, “limitations” refer to the shortcomings, constraints, or weaknesses within a study. A transparent reporting of such limitations can enhance the quality and reproducibility of research and improve public trust in science. However, authors often a) underreport them in the papers’ text and b) use hedging strategies to satisfy editorial requirements at the cost of readers’ clarity and confidence. This underreporting behavior, along with an explosion in the number of publications, has created a pressing need to automatically extract/generate such limitations from scholarly papers. In that direction, we report a complete architecture for computational analysis of research limitations. Specifically, we a) create a dataset of limitations in ACL, NeurIPS, and PeerJ papers by extracting them from papers’ text and integrating them with external reviews; b) propose methods to automatically generate them using a novel Retrieval Augmented Generation (RAG) technique; c) create a fine-grained evaluation framework for generated limitations and provide a meta-evaluation for the proposed evaluation techniques.

Downloads

Next from EMNLP 2025

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks

Similar lecture

Relation-Aware Prompting Makes Large Language Models Effective Zero-shot Relation Extractors