China

Large Language Models (LLMs) excel at generating synthetic data, but ensuring its quality and diversity remains challenging. We propose Genetic Prompt, a novel framework that innovatively combines genetic algorithms (GAs) with LLMs for synthetic data generation. Unlike previous GA approaches, Genetic Prompt implicitly represents semantic text attributes as gene sequences. Additionally, We implement an active learning scheme to optimize the GA process, eliminating traditional fitness evaluation and expanding offspring search space. Experiments on four relation extraction datasets show that Genetic Prompt significantly outperforms State-of-the-art baselines. Further more, analysis reveals that Genetic Prompt generates more diverse data with distributions closer to the gold dataset.

EMNLP 2025

Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

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."<br>

*Message from the General Chair, Dirk Hovy*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

Evaluating text generation capabilities of large language models (LLMs) is challenging, particularly for low-resource languages where methods for direct assessment are scarce. We propose MUG-Eval, a novel framework that evaluates LLMs' multilingual generation capabilities by transforming existing benchmarks into conversational tasks and measuring the LLMs' accuracies on those tasks. We specifically designed these conversational tasks to require effective communication in the target language. Then, we simply use task success rate as a proxy of successful conversation generation. Our approach offers two key advantages: it is independent of language-specific NLP tools or annotated datasets, which are limited for most languages, and it does not rely on LLMs-as-judges, whose evaluation quality degrades outside a few high-resource languages. We evaluate 8 LLMs across 30 languages spanning high, mid, and low-resource categories, and we find that MUG-Eval correlates strongly with established benchmarks (r > 0.75) while enabling standardized comparisons across languages and models. Our framework provides a robust and resource-efficient solution for evaluating multilingual generation that can be extended to thousands of languages.

MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language

Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive “System-1” tasks. We introduce Connector-Aware Compact CoT (CAC-CoT) --- a method that deliberately restricts reasoning to a small, fixed set of connector phrases, steering the model toward concise and well --- structured explanations. Despite its simplicity, our synthetic method with Gemini-2.0-Flash yields a high-quality training quality. CAC-CoT achieves approx 85\% on GSM8K and approx 40\% on GPQA (System-2) while retaining approx 90\% on S1-Bench (System-1). Its reasoning traces average approx 300 tokens(ART), about one-third the length of baseline traces, delivering higher efficiency without loss of accuracy.

CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks

While LLMs have been extensively studied on general text generation tasks, there is less research on text rewriting, a task related to general text generation, and particularly on the behavior of models on this task. In this paper we analyze what changes LLMs make in a text rewriting setting. We focus specifically on argumentative texts and their improvement, a task named Argument Improvement (ArgImp). We present CLEAR: an evaluation pipeline consisting of 57 metrics mapped to four linguistic levels: lexical, syntactic, semantic and pragmatic. This pipeline is used to examine the qualities of LLM-rewritten arguments on a broad set of argumentation corpora and compare the behavior of different LLMs on this task and analyze the behavior of different LLMs on this task in terms of linguistic levels. By taking all four linguistic levels into consideration, we find that the models perform ArgImp by shortening the texts while simultaneously increasing average word length and merging sentences. Overall we note an increase in the persuasion and coherence dimensions.

CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models

The emergence of large language models (LLMs) has brought a new paradigm to automated essay scoring (AES), a long-standing and practical application of natural language processing in education. However, achieving human-level multi-perspective understanding and judgment remains a challenge. In this work, we propose Roundtable Essay Scoring (RES), a multi-agent evaluation framework designed to perform precise and human-aligned scoring under a zero-shot setting. RES constructs evaluator agents based on LLMs, each tailored to a specific prompt and topic context. Each agent independently generates a trait-based rubric and conducts a multi-perspective evaluation. Then, by simulating a roundtable-style discussion, RES consolidates individual evaluations through a dialectical reasoning process to produce a final holistic score that more closely aligns with human evaluation. By enabling collaboration and consensus among agents with diverse evaluation perspectives, RES outperforms prior zero-shot AES approaches. Experiments on the ASAP dataset using ChatGPT and Claude show that RES achieves up to a 34.86% improvement in average QWK over straightforward prompting (Vanilla) methods.

LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring

Generative Large Language Models have emerged as useful tools, reshaping professional workflows. However, their efficacy in inherently complex and human-centric tasks such as leadership and strategic planning remains underexplored. In this interdisciplinary study, we present a novel dataset and compare LLMs and human leaders in the context of workplace action planning, specifically focusing on translating the abstract idea of inclusion into actionable SMART goals. We developed the Leader Success Bot, a script-based chatbot co-designed with domain experts, to guide more than 250 real-life leaders in generating inclusive workplace action plans. We systematically prompted seven state-of-the-art chat-based LLMs to perform the same task using the socio-demographic data of real-life leaders and instructions co-developed with domain experts. Our publicly released dataset enables direct comparison between human and LLM-generated workplace action plans, offering insights into their respective strengths, biases, and limitations. Our findings highlight critical gaps and opportunities for LLMs in leadership applications, fostering interdisciplinary collaboration and NLP applications.

Inclusive Leadership in the Age of AI: A Dataset and Comparative Study of LLMs vs. Real-Life Leaders in Workplace Action Planning

We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other available video benchmarks for its design, its reasoning categories, the metric it uses, and the language and culture of the videos. MAIA evaluates Vision Language Models (VLMs) on two aligned tasks: a visual statement verification task, and an open-ended visual question-answering task, both on the same set of video-related questions. It considers twelve reasoning categories that aim to disentangle language and vision relations by highlighting the role of the visual input. Thanks to its carefully taught design, it evaluates VLMs' consistency and visually grounded natural language comprehension and generation simultaneously through an aggregated metric revealing low results that highlight models' fragility. Last but not least, the video collection has been carefully selected to reflect the Italian culture, and the language data are produced by native-speakers.

All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark

Entity alignment (EA) involves identifying and linking equivalent entities across different knowledge graphs (KGs). While knowledge graphs provide structured information about real-world entities, only a small fraction of these entities are aligned. The entity alignment process is challenging due to heterogeneity in KGs, such as differences in structure, terminology, and attribute details. Traditional EA methods use multi-aspect entity embeddings to align entities. Although these methods perform well in certain scenarios, their effective- ness is often constrained by sparse or incomplete data in knowledge graphs and the limitations of embedding techniques. We propose ProLEA ( Profile Generation and Reasoning with LLMs for Entity Alignment) an entity alignment method that combines large language models (LLMs) with entity embed- dings. LLMs generate contextual profiles for entities based on their properties. Candidate entities identified by entity embedding techniques are then re-evaluated by the LLMs, using its background knowledge and the generated profile. A thresholding mechanism is introduced to resolve conflicts between LLMs predictions and embedding-based alignments. This method enhances alignment accuracy, robustness, and explainability, particularly for complex, het- erogeneous knowledge graphs. Furthermore, ProLEA is a generalized framework. Its profile generation and LLM-enhanced entity align- ment components can improve the performance of existing entity alignment models.

Entity Profile Generation and Reasoning with LLMs for Entity Alignment

Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes them thematically, and uses these to enrich an outline into an abstractive summary. To personalize summaries, we introduce SCOPE, a reason-out-loud protocol that has the model build a reasoning trace by answering nine questions before content selection. For evaluation, we propose P-MESA, a multi-dimensional, reference-free evaluation framework to assess if a summary fits a target reader. P-MESA reliably identifies error instances, achieving geq 89% balanced accuracy against human annotations and strongly aligned with human severity ratings (ρ geq 0.70). On QMSum and FAME, FRAME reduces hallucination and omission by 2 out of 5 points (measured with MESA), while SCOPE improves knowledge fit and goal alignment over prompt-only baselines. Our findings advocate for rethinking summarization to improve control, faithfulness, and personalization.

Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions

Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. However, the extent to which LRMs can think in other languages is less studied. This is as important as answer accuracy for real-world applications since users may find the thinking trace useful for oversight only if expressed in their languages. In this work, we comprehensively evaluate two leading families of LRMs on our established benchmark XReasoning. Surprisingly, even the most advanced models often revert to English or produce fragmented reasoning in other languages, revealing a substantial gap in the capability of thinking in non-English languages. Promoting models to reason in the user's language via prompt hacking enhances readability and oversight. This could gain user trust, but reduces answer accuracy, exposing an important trade-off. We further demonstrate that targeted post-training, even with just 100 instances, can mitigate this language mismatch, although accuracy is still degraded. Our results reveal the limited multilingual reasoning capabilities of current LRMs and suggest directions for future research. All code and datasets released at https://Anonymous.

When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy

Cross-lingual topic modeling (CLTM) is an essential task in the field of data mining and natural language processing, aiming to extract aligned and semantically coherent topics from bilingual corpora. Recent advances in cross-lingual neural topic models have widely leveraged bilingual dictionaries to achieve word-level topic alignment. However, two critical challenges remain in cross-lingual topic modeling, the topic mismatch issue and the degeneration of intra-lingual topic interpretability. Due to linguistic diversity, some translated word pairs may not represent semantically coherent topics despite being lexical equivalents, and the objective of cross-lingual topic alignment in CLTM can consequently degrade topic interpretability within intra languages. To address these issues, we propose a novel document-level prototype-based contrastive learning paradigm for cross-lingual topic modeling. Additionally, we design a retrieval-based positive sampling strategy for contrastive learning without data augmentation. Furthermore, we introduce ProtoXTM, a cross-lingual neural topic model based on document-level prototype-based contrastive learning. Extensive experiments indicate that our approach achieves state-of-the-art performance on cross-lingual and mono-lingual benchmarks, demonstrating enhanced topic interpretability.

Downloads

Next from EMNLP 2025

MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES