China

Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing interactive clarification approaches face two critical limitations: reliance on manually constructed datasets, which inherently constrains training data scale and diversity, and lack of error correction mechanisms during multi-turn clarification, leading to error accumulation that compromises both accuracy and efficiency. We present AskToAct, which addresses these challenges by exploiting the structural mapping between queries and their tool invocation solutions. Our key insight is that tool parameters naturally represent explicit user intents. By systematically removing key parameters from queries while retaining them as ground truth, we enable automated construction of high-quality training data. We further enhance model robustness through error-correction pairs and selective masking, enabling dynamic error detection during clarification interactions. Comprehensive experiments demonstrate that AskToAct significantly outperforms existing approaches, achieving above 57% accuracy in recovering critical unspecified intents and enhancing clarification efficiency by an average of 10.46% while maintaining high accuracy in tool invocation. Our framework exhibits robust performance across different model architectures and successfully generalizes to entirely unseen APIs without additional training, achieving performance comparable to GPT-4o with substantially fewer computational resources.

EMNLP 2025

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification

tool learning

self-correction

dialogue and interactive systems

### 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)

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.

With the rise of mental health challenges, social media has become a key platform for emotional expression. Deep learning offers a promising solution for analyzing mental health but lacks flexibility and interpretability. Large language models (LLMs) introduce greater adaptability and can explain their decisions, yet they still underperform deep learning in complex psychological analysis. We present C-IMHI, the first multi-task Chinese social media interpretable mental health instruction dataset (9K samples) with quality control and manual validation. Additionally, we introduce MentalGLM, the first open-source Chinese LLMs for explainable mental health analysis, trained on 50K instructions. The proposed models excelled in three mental health downstream tasks, outperforming or matching deep learning and LLMs. A portion of the generated decision explanations was validated by experts, demonstrating promising accuracy and reliability. We evaluated the proposed models on a clinical dataset, where they significantly outperformed other LLMs, demonstrating their potential for clinical applications. Our models show strong performance, validated across tasks and domains. The decision explanations enhance usability and facilitate better understanding and practical application of the models. Both the constructed dataset and the models are publicly available via: https://anonymous.4open.science/r/MentalGLM-F416.

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media

The widespread deployment of large language models (LLMs) across various domains has made their safety a critical priority. Inspired by think-tank decision-making philosophy, we propose DiplomacyAgent, an LLM-based multi-agent system for diplomatic position analysis. With DiplomacyAgent, we are able to systematically assess how LLMs balance “interests” against “ethical principles” when addressing various international events, hence understanding the safety implications of LLMs in diplomacy. Specifically, this will help to assess the consistency of LLM stance with globally recognized ethical standards, as well as the potential risks or ideological biases that may arise. Through integrated quantitative metrics, our research uncovers unexpected decision-making patterns in LLM responses to sensitive issues including human rights protection, environmental sustainability, regional conflicts, etc. It discloses that LLMs could exhibit a strong bias towards interests, leading to unsafe decisions that violate ethical and moral principles. Our experiment results suggest that deploying LLMs in high-stakes domains, particularly in the formulation of diplomatic policies, necessitates a comprehensive assessment of potential moral and social implications, as well as the implementation of stringent safety protocols. Our codes and data will be publicly released soon.

DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events?

Converging societal and technical factors have transformed language technologies into user-facing applications employed across languages. Machine Translation (MT) has become a global tool, with cross-lingual services now also supported by dialogue systems powered by multilingual Large Language Models (LLMs). Such accessibility has expanded MT’s reach to a vast base of lay users, often with little to no expertise in the languages or the technology itself. And yet, the understanding of MT consumed by this diverse group of users—their needs, experiences, and interactions with these systems—remains limited. We trace the shift in MT user profiles, focusing on non-expert users and how their engagement with these systems may change with LLMs. We identify three key factors—usability, trust, and literacy—that shape these interactions and must be addressed to align MT with user needs. By exploring these dimensions, we offer insights to guide future MT with a user-centered approach.

Translation in the Hands of Many: Centering Lay Users in Machine Translation Interactions

Recent spoken dialogue systems employ large language models with advanced reasoning capabilities as their core architecture. However, there exists a discrepancy between optimal textual and verbal delivery, which presents challenges in effectively leveraging the reasoning process for spoken communication. Although some efforts aim to adapt language models for more speech-suitable delivery, the impact of these modifications on the models' reasoning capabilities remains underexplored. In this work, we propose the Think-Verbalize-Speak framework that separates the reasoning process from the spoken content to fully harness the reasoning capabilities of LLMs in spoken dialogue. Specifically, we introduce an intermediate step between thinking and speaking, termed \textit{verbalizing}, in which the thought process is translated into comprehensible text. We also present ReVerT, a latency-efficient implementation of the verbalizer using incremental and asynchronous summarization. Extensive automatic and human evaluations across multiple benchmarks demonstrate that our approach improves speech naturalness and conciseness with minimal compromise to reasoning capabilities. We release both the dataset and its construction pipeline to facilitate future research.

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech

Effective interactions between artificial intelligence (AI) and humans require an equitable and accurate representation of diverse cultures. It is known that current AI, particularly large language models (LLMs), possesses some degrees of cultural knowledge but not without limitations. We present a framework aimed at understanding the origin of these limitations. We hypothesize that there is a fundamental discordance between embedded ethics—how LLMs represent right versus wrong, and cultural inference—how LLMs infer cultural knowledge, specifically cultural norms. We demonstrate this by extracting low-dimensional subspaces that embed ethical principles of LLMs based on established benchmarks. We then show that how LLMs make errors in culturally distinctive scenarios significantly correlates with how they represent cultural norms with respect to these embedded ethics subspaces. Furthermore, we show that coercing cultural norms to be more aligned with the embedded ethics increases LLM performance in cultural inference. Our analyses of 12 language models, two large-scale cultural benchmarks spanning 75 countries and two ethical datasets indicate that 1) the ethics-culture discordance tends to be exacerbated in instruct-tuned models, and 2) how current LLMs represent ethics can impose limitations on their adaptation to diverse cultures particularly pertaining to non-Western and low-income regions.

The discordance between embedded ethics and cultural inference in large language models

Recent studies have explored the use of large language models (LLMs) in psychotherapy; however, text-based cognitive behavioral therapy (CBT) models often struggle with client resistance, which can weaken therapeutic alliance. To address this, we propose a multimodal approach that incorporates nonverbal cues, which allows the AI therapist to better align its responses with the client's negative emotional state. Specifically, we introduce a new synthetic dataset, Mirror (Multimodal Interactive Rolling with Resistance), which is a novel synthetic dataset that pairs each client's statements with corresponding facial images. Using this dataset, we train baseline vision language models (VLMs) so that they can analyze facial cues, infer emotions, and generate empathetic responses to effectively manage client resistance. These models are then evaluated in terms of both their counseling skills as a therapist, and the strength of therapeutic alliance in the presence of client resistance. Our results demonstrate that Mirror significantly enhances the AI therapist’s ability to handle resistance, which outperforms existing text-based CBT approaches. Human expert evaluations further confirm the effectiveness of our approach in managing client resistance and fostering therapeutic alliance.

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance

The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking. Despite advancements in Large Language Models (LLMs) that enhance automated reasoning, their application to misinformation detection remains hindered by issues of logical inconsistency and superficial verification. In response, we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate. Inspired by fact-checking workflows, D2D assigns domain-specific profiles to each agent and orchestrates a five-stage debate process, including Opening Statement, Rebuttal, Free Debate, Closing Statement, and Judgment. To transcend traditional binary classification, D2D introduces a multi-dimensional evaluation mechanism that assesses each claim across five distinct dimensions: Factuality, Source Reliability, Reasoning Quality, Clarity, and Ethics. Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods, and the case study highlight D2D's capability to iteratively refine evidence while improving decision transparency, representing a substantial advancement towards robust and interpretable misinformation detection. Our code is available at \href{https://anonymous.4open.science/r/emnlp_d2d-36E2/}{\texttt{4open.science/emnlp\_d2d-36E2}}.

Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments that require long-horizon adaptability. By retaining partial diversity, systems can better explore novel strategies and cope with external shocks. We formalize a consensus-diversity tradeoff, showing conditions where implicit methods outperform explicit ones. Experiments on three scenarios -- Dynamic Disaster Response, Information Spread and Manipulation, and Dynamic Public-Goods Provision -- confirm partial deviation from group norms boosts exploration, robustness, and performance. We highlight emergent coordination via in-context learning, underscoring the value of preserving diversity for resilient decision-making.

The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems

Large language models (LLMs) often exhibit societal biases in their outputs, prompting ethical concerns regarding fairness and harm. In this work, we propose KLAAD (KL-Attention Alignment Debiasing), an attention-based debiasing framework that implicitly aligns attention distributions between stereotypical and anti-stereotypical sentence pairs without directly modifying model weights. KLAAD introduces a composite training objective combining Cross-Entropy, KL divergence, and Triplet losses, guiding the model to consistently attend across biased and unbiased contexts while preserving fluency and coherence. Experimental evaluation of KLAAD demonstrates improved bias mitigation on both the BBQ and BOLD benchmarks, with minimal impact on language modeling quality. The results indicate that attention-level alignment offers a principled solution for mitigating bias in generative language models.

KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models

Understanding the overall stance of news articles is challenging due to their length and structural complexity. Yet, it is essential for supporting pluralistic and credible media environments. This paper introduces a novel stance detection dataset for Korean news, featuring annotations at both the article level and the segment level, informed by the narrative structure of news articles. Building on this resource, we propose an agentic in-context learning method that prompts a large language model (LLM) with segment-level stance predictions generated by a language model agent. Experiments across multiple LLMs demonstrate the effectiveness of the proposed framework for article-level stance detection and highlight its broader utility in enhancing diverse news recommendations and analyzing patterns of media bias.

Downloads

Next from EMNLP 2025

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media

Similar lecture

ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems