Austria

Large Language Models (LLMs) have shown remarkable capabilities in knowledge-intensive tasks, while they remain vulnerable when encountering misinformation. Existing studies have explored the role of LLMs in combating misinformation, but there is still a lack of fine-grained analysis on the specific aspects and extent to which LLMs are influenced by misinformation. To bridge this gap, we present MisBench, the current largest and most comprehensive benchmark for evaluating LLMs&#39; behavior and knowledge preference toward misinformation. MisBench consists of 10,346,712 pieces of misinformation, which uniquely considers both knowledge-based conflicts and stylistic variations in misinformation. Empirical results reveal that while LLMs demonstrate comparable abilities in discerning misinformation, they still remain susceptible to knowledge conflicts and stylistic variations. Based on these findings, we further propose a novel approach called Reconstruct to Discriminate (RtD) to strengthen LLMs&#39; ability to detect misinformation. Our study provides valuable insights into LLMs&#39; interactions with misinformation, and we believe MisBench can serve as an effective benchmark for evaluating LLM-based detectors and enhancing their reliability in real-world applications. Codes and data are available at: https://github.com/GKNL/MisBench.

ACL 2025

How does Misinformation Affect Large Language Model Behaviors and Preferences?

knowledge preference

large language model

misinformation

## 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.

Large Language Models (LLMs) have shown remarkable capabilities in knowledge-intensive tasks, while they remain vulnerable when encountering misinformation. Existing studies have explored the role of LLMs in combating misinformation, but there is still a lack of fine-grained analysis on the specific aspects and extent to which LLMs are influenced by misinformation. To bridge this gap, we present MisBench, the current largest and most comprehensive benchmark for evaluating LLMs' behavior and knowledge preference toward misinformation. MisBench consists of 10,346,712 pieces of misinformation, which uniquely considers both knowledge-based conflicts and stylistic variations in misinformation. Empirical results reveal that while LLMs demonstrate comparable abilities in discerning misinformation, they still remain susceptible to knowledge conflicts and stylistic variations. Based on these findings, we further propose a novel approach called Reconstruct to Discriminate (RtD) to strengthen LLMs' ability to detect misinformation. Our study provides valuable insights into LLMs' interactions with misinformation, and we believe MisBench can serve as an effective benchmark for evaluating LLM-based detectors and enhancing their reliability in real-world applications. Codes and data are available at: https://github.com/GKNL/MisBench.

poster

### 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**. 

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

Medical Vision-Language Models (Med-VLMs) have achieved success across various tasks, yet most existing methods overlook the modality misalignment issue that can lead to untrustworthy responses in clinical settings. 
In this paper, we propose Hierarchical Self-Contrastive Rewarding (HSCR), a novel approach that addresses two critical challenges in Med-VLM alignment: 1) Cost-effective generation of high-quality preference data; 2) Capturing nuanced and context-aware preferences for improved alignment. 
HSCR first leverages the inherent capability of Med-VLMs to generate dispreferred responses with higher sampling probability. By analyzing output logit shifts after visual token dropout, we identify modality-coupled tokens that induce misalignment and derive an implicit alignment reward function. This function guides token replacement with hallucinated ones during decoding, producing high-quality dispreferred data. Furthermore, HSCR introduces a multi-level preference optimization strategy, which extends beyond traditional adjacent-level optimization by incorporating nuanced implicit preferences, leveraging relative quality in dispreferred data to capture subtle alignment cues for more precise and context-aware optimization. Extensive experiments across multiple medical tasks, including Med-VQA, medical image captioning and instruction following, demonstrate that HSCR not only enhances zero-shot performance but also significantly improves modality alignment and trustworthiness with just 2,000 training entries. Code is released on https://github.com/jiangsongtao/HSCR.

HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving black-box feedback APIs, limited queries, or multiple task types. To bridge this gap, we propose \textbf{C}luster and \textbf{E}nsemble \textbf{M}util-task Text Adversarial \textbf{A}ttack (\textbf{CEMA}), an effective black-box attack that exploits the transferability of adversarial texts across different tasks. CEMA simplifies complex multi-task scenarios by using a \textit{deep-level substitute model} trained in a \textit{plug-and-play} manner for text classification, enabling attacks without mimicking the victim model. This approach requires only a few queries for training, converting multi-task attacks into classification attacks and allowing attacks across various tasks. CEMA generates multiple adversarial candidates using different text classification methods and selects the one that most effectively attacks substitute models. In experiments involving multi-task models with two, three, or six tasks—spanning classification, translation, summarization, and text-to-image generation—CEMA demonstrates significant attack success with as few as 100 queries. Furthermore, CEMA can target commercial APIs (e.g., Baidu and Google Translate), large language models (e.g., ChatGPT 4o), and image-generation models (e.g., Stable Diffusion V2), showcasing its versatility and effectiveness in real-world applications.

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries

Human traveling trajectories play a central role in characterizing each travelogue, and automatic trajectory extraction from travelogues is highly desired for tourism services, such as travel planning and recommendation. This work addresses the extraction of human traveling trajectories from travelogues. Previous work treated each trajectory as a sequence of visited locations, although locations with different granularity levels, e.g., "Kyoto City" and "Kyoto Station," should not be lined up in a sequence. In this work, we propose to represent the trajectory as a graph that can capture the hierarchy as well as the visiting order, and construct a benchmark dataset for the trajectory extraction. The experiments using this dataset show that even naive baseline systems can accurately predict visited locations and the visiting order between them, while it is more challenging to predict the hierarchical relations.

Graph-Structured Trajectory Extraction from Travelogues

With the rapid adoption of large language models (LLMs) in natural language processing, the ability to follow instructions has emerged as a key metric for evaluating their practical utility. However, existing evaluation methods often focus on single-language scenarios, overlooking the challenges and differences present in multilingual and cross-lingual contexts. To address this gap, we introduce MaXIFE: a comprehensive evaluation benchmark designed to assess instruction-following capabilities across 23 different languages with 1667 verifiable instruction tasks. MaXIFE integrates both Rule-Based Evaluation and Model-Based Evaluation, ensuring a balance of efficiency and accuracy. We applied MaXIFE to evaluate several leading commercial LLMs, establishing baseline results for future comparisons. By providing a standardized tool for multilingual instruction-following evaluation, MaXIFE aims to advance research and development in natural language processing.

MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation

Despite having a population of twenty million, Kazakhstan's culture and language remain underrepresented in the field of natural language processing. Although large language models (LLMs) continue to advance worldwide, progress in Kazakh language has been limited, as seen in the scarcity of dedicated models and benchmark evaluations. To address this gap, we introduce KazMMLU, the first MMLU-style dataset specifically designed for Kazakh language. KazMMLU comprises 23,000 questions that cover various educational levels, including STEM, humanities, and social sciences, sourced from authentic educational materials and manually validated by native speakers and educators. The dataset includes 10,969 Kazakh questions and 12,031 Russian questions, reflecting Kazakhstan's bilingual education system and rich local context. Our evaluation of several state-of-the-art multilingual models (Llama3.1, Qwen-2.5, GPT-4, and DeepSeek V3) demonstrates substantial room for improvement, as even the best-performing models struggle to achieve competitive performance in Kazakh and Russian. These findings highlight significant performance gaps compared to high-resource languages. We hope that our dataset will enable further research and development of Kazakh-centric LLMs.

KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan

Instruction tuning in low-resource languages remains underexplored due to limited text data, particularly in government and cultural domains. To address this, we introduce and open-source a large-scale (10,600 samples) instruction-following (IFT) dataset, covering key institutional and cultural knowledge relevant to Kazakhstan. Our dataset enhances LLMs' understanding of procedural, legal, and structural governance topics. We employ LLM-assisted data generation, comparing open-weight and closed-weight models for dataset construction, and select GPT-4o as the backbone. Each entity of our dataset undergoes full manual verification to ensure high quality. We also show that fine-tuning Qwen, Falcon, and Gemma on our dataset leads to consistent performance improvements in both multiple-choice and generative tasks, demonstrating the potential of LLM-assisted instruction tuning for low-resource languages.

Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating different domain datasets. However, existing continual DAP methods face several limitations: (1) high computational cost and GPU memory usage during training; (2) sensitivity to incremental data order; and (3) providing a single, generalized model for all end tasks, which contradicts the essence of DAP. In this paper, we propose DoMIX, a novel approach that addresses these challenges by leveraging LoRA modules, a representative parameter-efficient fine-tuning (PEFT) method. Our approach enables efficient and parallel domain-adaptive pre-training that is robust to domain order and effectively utilizes accumulated knowledge to provide tailored pre-trained models for specific tasks.
We also demonstrate that our method can be extended beyond the DAP setting to standard LLM fine-tuning scenarios. Code is available at https://github.com/dohoonkim-ai/DoMIX.

DoMIX: An Efficient Framework for Exploiting Domain Knowledge in Fine-Tuning

We introduce CoT-ICL Lab, a framework and methodology to generate synthetic tokenized datasets and systematically study chain-of thought (CoT) in-context learning (ICL) in language models. CoT-ICL Lab allows fine grained control over the complexity of in-context examples by decoupling (1) the causal structure involved in chain token generation from (2) the underlying token processing functions. We train decoder-only transformers (up to 700M parameters) on these datasets and show that CoT accelerates the accuracy transition to higher values across model sizes. In particular, we find that model depth is crucial for leveraging CoT with limited in-context examples, while more examples help shallow models match deeper model performance. Additionally, limiting the diversity of token processing functions throughout training improves causal structure learning via ICL. We also interpret these transitions by analyzing transformer embeddings and attention maps. Overall, CoT-ICL Lab serves as a simple yet powerful testbed for theoretical and empirical insights into ICL and CoT in language models.

CoT-ICL Lab: A Petri Dish for Studying Chain-of-Thought Learning from In-Context Demonstrations

Large language models (LLMs) have revolutionized artificial intelligence, but their performance on specific tasks is often limited by knowledge boundaries. While fine-tuning techniques like low-rank adaptation (LoRA) aim to address this, they can suffer from overfitting. We propose flexible low-rank adaptation (Flexora), a novel method that automatically selects the most critical layers for fine-tuning to optimize performance across diverse downstream tasks. Flexora formulates layer selection as a hyperparameter optimization problem, employs unrolled differentiation for efficient solving, and identifies the most impactful layers based on optimized hyperparameters. Extensive experiments across various pre-trained models and natural language tasks demonstrate that Flexora consistently outperforms existing baselines. We provide theoretical insights and comprehensive ablation studies to elucidate the effectiveness of Flexora. Therefore, Flexora offers a robust solution to enhance LoRA fine-tuning for LLMs, potentially advancing the field of adaptive language model optimization.

Flexora: Flexible Low-Rank Adaptation for Large Language Models

Question answering (QA) tasks serve as a key benchmark for evaluating generation systems. Traditional rule-based metrics, such as accuracy and relaxed-accuracy, struggle with open-ended and unstructured responses. LLM-based evaluation methods offer greater flexibility but suffer from sensitivity to instructions, robustness issues, and high computational costs. To overcome these challenges, we introduce QAEval, a hybrid framework combining rule-based reliability with LLM-based adaptability. QAEval utilizes two high-quality datasets: QAExtract for short-answer extraction and QAScore for scoring model training. By integrating a Mixture of Evaluators model with Dynamic Load Balancing Optimization, QAEval enables accurate, cost-effective QA evaluation. Experimental results show it outperforms models like GPT-4o and Claude-3, achieving 92.3% accuracy with only 0.6B parameters.

Downloads

Next from ACL 2025

HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models

Similar lecture

Unraveling Misinformation Propagation in LLM Reasoning