China

Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms have shown that LLMs can improve by judging their own responses instead of relying on human labelers. However, existing methods have primarily focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. To address this issue, we introduce a novel Meta-Rewarding step to the self-improvement process, where the model judges its own judgements and uses that feedback to refine its judgment skills. Surprisingly, this unsupervised approach improves the model&#39;s ability to judge and follow instructions, as demonstrated by a win rate improvement of Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2, and 20.6% to 29.1% on Arena-Hard. These results strongly suggest the potential for self-improving models without human supervision.

EMNLP 2025

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

self improve

rlaif

rlhf

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms have shown that LLMs can improve by judging their own responses instead of relying on human labelers. However, existing methods have primarily focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. To address this issue, we introduce a novel Meta-Rewarding step to the self-improvement process, where the model judges its own judgements and uses that feedback to refine its judgment skills. Surprisingly, this unsupervised approach improves the model's ability to judge and follow instructions, as demonstrated by a win rate improvement of Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2, and 20.6% to 29.1% on Arena-Hard. These results strongly suggest the potential for self-improving models without human supervision.

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.

Quantifying identity fusion---the psychological merging of self with another entity or abstract target (e.g., a religious group, political party, ideology, value, brand, belief, etc.)---is vital for understanding a wide range of group‑based human behaviors. We introduce the Cognitive Linguistic Identity Fusion Score (CLIFS), a novel metric that integrates cognitive linguistics with large language models (LLMs), which builds on implicit metaphor detection. Unlike traditional pictorial and verbal scales, which require controlled surveys or direct field contact, CLIFS delivers fully automated, scalable assessments while maintaining strong alignment with the established verbal measure. In benchmarks, CLIFS outperforms both existing automated approaches and human annotation. As a proof of concept, we apply CLIFS to violence risk assessment to demonstrate that it can improve violence risk assessment by more than 240%. Building on our identification of a new NLP task and early success, we underscore the need to develop larger, more diverse datasets encompassing additional fusion-target domains and cultural backgrounds to enhance generalizability and further advance this emerging area.

Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition‑Informed Approach to Quantifying Identity Fusion from Text

Visual Language Models have demonstrated remarkable capabilities across various tasks, including visual question answering and image captioning. However, most models rely on text-based instructions, limiting their effectiveness in natural human-machine interactions. Moreover, the quality of language models primarily depends on reasoning and prompting techniques, such as chain-of-thought, which remain underexplored when using speech instructions. To address these challenges, we propose SilVar, an end-to-end multimodal model that leverages speech instructions for reasoning-based visual question answering. Additionally, we investigate reasoning techniques at different levels, including conversational, simple, and complex speech instructions. SilVar is built upon CLIP, Whisper, and LLaMA 3.1-8B, enabling more intuitive interactions by allowing users to provide verbal or text-based instructions. To this end, we introduce a new dataset designed to challenge models with speech-based reasoning tasks for object localization. This dataset enhances the model’s ability to process and explain visual scenes from spoken input, moving beyond simple object recognition to reasoning-based interactions. To the best of our knowledge, SilVar is the first open-source, speech-driven VLM. Despite the challenges posed by speech-based instructions, experiments show that our speech-driven multimodal model performs on par with text-based models of similar size on the MMMU and ScienceQA benchmarks, demonstrating its potential in scenarios where text input is unavailable or not preferred, such as self-driving cars and medical surgery. We believe SilVar will inspire the next generation of multimodal reasoning models, advancing toward expert artificial general intelligence.

SilVar: Speech-Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization

In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and give signals for human input. However, the reliability of these models has not yet been thoroughly explored. Thus, we propose and test an attack, \RedHerring. RedHerring aims to make attack detection models unreliable by modifying a text to cause the detection model to predict an attack, while keeping the classifier correct. This creates a tension between the classifier and detector. If a human sees that the detector is giving an ``incorrect'' prediction, but the classifier a correct one, then the human will see the detector as unreliable. We test this novel threat model on 4 datasets against 3 detectors defending 4 classifiers. We find that RedHerring is able to drop detection accuracy between 20 - 71 points, while maintaining (or improving) classifier accuracy. As an initial defense, we propose a simple confidence check which requires no retraining of the classifier or detector and increases detection accuracy greatly. This novel threat model offers new insights into how adversaries may target detection models.

RedHerring Attack: Testing the Reliability of Attack Detection

Language models (LMs), like other neural networks, often favor shortcut heuristics based on surface-level patterns. LMs in particular behave like n-gram models early in training, but eventually learn hierarchical syntax to correctly apply grammatical rules out-of-distribution (OOD). This paper uses case studies of English grammar to explore how complex, diverse training data drives OOD generalization. We construct a framework that unifies our understanding of random variation with training dynamics, rule selection with memorization, and data diversity with complexity. We show that these factors are nuanced, and that intermediate levels of diversity and complexity lead to inconsistent behavior across random seeds and to unstable training dynamics. Our findings emphasize the critical role of training data in shaping generalization patterns and illuminate how competing model strategies lead to inconsistent training outcomes.

Data Drives Unstable Hierarchical Generalization in LMs

Multilingual speech translation (ST) in the medical domain enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating improved diagnosis and treatment, particularly during pandemics. In this work, we present the first systematic study on medical ST, to our best knowledge, by releasing MultiMed-ST, a large-scale ST dataset for the medical domain, spanning all translation directions in five languages: Vietnamese, English, German, French, Traditional Chinese and Simplified Chinese, together with the models. With 290,000 samples, our dataset is the largest medical machine translation (MT) dataset and the largest many-to-many multilingual ST among all domains. Secondly, we present the most extensive analysis study in ST research to date, including: empirical baselines, bilingual-multilingual comparative study, end-to-end vs. cascaded comparative study, task-specific vs. multi-task sequence-to-sequence (seq2seq) comparative study, code-switch analysis, and quantitative-qualitative error analysis. All code, data, and models are available online.

MultiMed-ST: Large-scale Many-to-many Multilingual Medical Speech Translation

The rapid advancement of Large Language Models (LLMs) has revolutionized text generation but also raised concerns about potential misuse, making detecting LLM-generated text (AI text) increasingly essential. While prior work has focused on identifying AI text and effectively textitcheckmating it, our study investigates a less-explored territory: portraying the nuanced distinctions between human and AI texts across text segments (introduction, body, and conclusion). Whether LLMs excel or falter in incorporating linguistic ingenuity across text segments, the results will critically inform their viability and boundaries as effective creative assistants to humans. Through an analogy with the structure of chess games, comprising opening, middle, and end games, we analyze segment-specific patterns to reveal where the most striking differences lie. Although AI texts closely resemble human writing in the body segment due to its length, deeper analysis shows a higher divergence in features dependent on the continuous flow of language, making it the most informative segment for detection. Additionally, human texts exhibit greater stylistic variation across segments, offering a new lens for distinguishing them from AI. Overall, our findings provide fresh insights into human-AI text differences and pave the way for more effective and interpretable detection strategies. Codes available at https://simpleurl.tech/TGKBi.

Beyond Checkmate: Exploring the Creative Choke Points for AI Generated Texts

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, **DualDistill**, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train **Agentic-R1**, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems and using text-based reasoning for abstract ones. Our method improves accuracy on computation-intensive tasks and reduces inference latency on standard benchmarks, demonstrating the promise of multi-strategy distillation for robust and efficient reasoning.

Agentic-R1: Distilled Dual-Strategy Reasoning

Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond. However, simply extending the input sequence length does not necessarily lead to effective long-context understanding. In this study, we integrate Chain-of-Thought (CoT) reasoning into LLMs in a supervised manner to facilitate effective long-context understanding. To achieve this, we introduce LongFinanceQA, a synthetic dataset in the financial domain designed to improve long-context reasoning. Unlike existing long-context synthetic data, LongFinanceQA includes intermediate CoT reasoning before the final conclusion, which encourages LLMs to perform explicit reasoning, improving accuracy and interpretability in long-context understanding. To generate synthetic CoT reasoning, we propose Property-based Agentic Inference (PAI), an agentic framework that simulates human-like reasoning steps, including property extraction, retrieval, and summarization. We evaluate PAI's reasoning capabilities by assessing GPT-4o-mini w/ PAI on the Loong benchmark, outperforming standard GPT-4o-mini by 20.0%. Furthermore, we fine-tune LLaMA-3.1-8B-Instruct on LongFinanceQA, achieving a 28.0% gain on Loong's financial subset.

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning

Sycophancy causes models to produce answers that cater to user expectations rather than providing truthful responses. Sycophantic behavior in models can erode user trust by creating a perception of dishonesty or bias. This lack of authenticity may lead users to question the reliability and objectivity of the system's responses. Although Reinforcement Learning from Human Feedback (RLHF) is effective in aligning models with human preferences, previous studies have observed that it can simultaneously amplify sycophantic behavior. However, these studies primarily focused on proprietary models and employed indirect analysis to demonstrate the influence of human feedback. Our study focuses on sycophancy in open-source models, which are more reproducible and transparent for research. We investigated the impact of human feedback on sycophancy by directly comparing models aligned with human feedback to those not aligned. To address sycophancy, we proposed assessing the user's expected answer rather than ignoring it. Consequently, we developed the Sycophancy Answer Assessment (SAA) dataset and introduced Self-Augmented Preference Alignment, demonstrating that these methods effectively enhance the model's assessment ability and significantly reduce sycophancy across tasks.

Self-Augmented Preference Alignment for Sycophancy Reduction in LLMs

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most apply broad, surface-level fixes and can therefore easily be circumvented by jailbreak attacks. In this paper we leverage sparse autoencoders (SAEs) to identify toxicity-related directions in the residual stream of models and perform targeted activation steering using the corresponding decoder vectors. We introduce three tiers of steering aggressiveness and evaluate them on GPT-2 Small and Gemma-2-2B, revealing trade-offs between toxicity reduction and language fluency. At stronger steering strengths, these causal interventions surpass competitive baselines in reducing toxicity by up to 20%, though fluency can degrade noticeably on GPT-2 Small depending on the aggressiveness. Crucially, standard NLP benchmark scores upon steering remain stable, indicating that the model’s knowledge and general abilities are preserved. We further show that feature-splitting in wider SAEs hampers safety interventions, underscoring the importance of disentangled feature learning. Our findings highlight both the promise and the current limitations of SAE-based causal interventions for LLM detoxification, further suggesting practical guidelines for safer language-model deployment.

Downloads

Next from EMNLP 2025

Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition‑Informed Approach to Quantifying Identity Fusion from Text

Similar lecture

Process-based Self-Rewarding Language Models