China

LLM-as-a-judge has become a promising paradigm for evaluating natural language generation (NLG), but the lack of reliability limits its deployment in high-risk applications. It has been very common to use LLMs to directly evaluate LLM-generated content while uncertainty quantification for rating evaluation remains underexplored. This work presents the first analysis framework to offer interval evaluations in LLM-based scoring via conformal prediction. Conformal prediction constructs continuous confidence intervals from a single evaluation run and we design an ordinal boundary adjustment for discrete rating tasks. We also suggest a midpoint-based score within the interval as a low-bias alternative to raw model score and weighted average. Extensive experiments and analysis across evaluators and conformal prediction methods show that our framework yields narrow intervals with reliable coverage, enabling more trustworthy evaluation for downstream decision making.

EMNLP 2025

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction

llm-as-a-judge

conformal prediction

uncertainty quantification

automatic evaluation

### 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.

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

As people increasingly use AI systems in work and daily life, feedback mechanisms that help them use AI responsibly are urgently needed, particularly in settings where users are not equipped to assess the quality of AI predictions. We study a realistic Machine Translation (MT) scenario where monolingual users decide whether to share an MT output, first without and then with quality feedback. We compare four types of quality feedback: explicit feedback that directly give users an assessment of translation quality using 1) error highlights and 2) LLM explanations, and implicit feedback that helps users compare MT inputs and outputs through 3) backtranslation and 4) question–answer (QA) tables. We find that all feedback types, except error highlights, significantly improve both decision accuracy and appropriate reliance. Notably, implicit feedback, especially QA tables, yields significantly greater gains than explicit feedback in terms of decision accuracy, appropriate reliance, and user perceptions -- receiving the highest ratings for helpfulness and trust, and the lowest for mental burden.

Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation

Minority languages in China, such as Tibetan, Uyghur, and Traditional Mongolian, face significant challenges due to their unique writing systems, which differ from international standards. This discrepancy has led to a severe lack of relevant corpora, particularly for supervised tasks like headline generation. To address this gap, we introduce a novel dataset, Chinese Minority Headline Generation (CMHG), which includes 100,000 entries for Tibetan, and 50,000 entries each for Uyghur and Mongolian, specifically curated for headline generation tasks. Additionally, we propose a high-quality test set annotated by native speakers, designed to serve as a benchmark for future research in this domain. We hope this dataset will become a valuable resource for advancing headline generation in Chinese minority languages and contribute to the development of related benchmarks.

CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China

The communication topology in large language model-based multi-agent systems fundamentally governs inter-agent collaboration patterns, critically shaping both the efficiency and effectiveness of collective decision-making. While recent studies for communication topology automated design tend to construct sparse structures for efficiency, they often overlook why and when sparse and dense topologies help or hinder collaboration. In this paper, we present a causal framework to analyze how agent outputs, whether correct or erroneous, propagate under topologies with varying sparsity. Our empirical studies reveal that moderately sparse topologies, which effectively suppress error propagation while preserving beneficial information diffusion, typically achieve optimal task performance. Guided by this insight, we propose a novel topology design approach, EIB-Learner, that balances error suppression and beneficial information propagation by fusing connectivity patterns from both dense and sparse graphs. Extensive experiments show the superior effectiveness, communication cost, and robustness of EIB-Learner.

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems

Large language models (LLMs) have shown promise in automating travel planning, yet they often fall short in addressing nuanced spatiotemporal rationality. While existing benchmarks focus on basic plan validity, they neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability. This paper introduces **TP-RAG**, the first benchmark tailored for retrieval-augmented, spatiotemporal-aware travel planning. Our dataset includes 2,348 real-world travel queries, 85,575 fine-grain annotated POIs, and 18,784 high-quality travel trajectory references sourced from online tourist documents, enabling dynamic and context-aware planning. Through extensive experiments, we reveal that integrating reference trajectories significantly improves spatial efficiency and POI rationality of the travel plan, while challenges persist in universality and robustness due to conflicting references and noisy data. To address these issues, we propose *EvoRAG*, an evolutionary framework that potently synergizes diverse retrieved trajectories with LLMs' intrinsic reasoning. *EvoRAG* achieves state-of-the-art performance, improving spatiotemporal compliance and reducing commonsense violation compared to ground-up and retrieval-augmented baselines. Our work underscores the potential of hybridizing Web knowledge with LLM-driven optimization, paving the way for more reliable and adaptive travel planning agents.

TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning

Large language models (LLMs) have shown promising capabilities in first-order logic (FOL) reasoning, with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deductions is still under-researched. While LLMs perform competitively on established mathematical reasoning benchmarks, they struggle with multi-step FOL tasks, as demonstrated by Deepseek-Prover-V2-7B's low accuracy (4.1\%) on our proposed theorem proving dataset. This issue arises from limited exploration of diverse proof strategies and the potential for early reasoning mistakes to undermine entire proofs. To address these issues, we propose DREAM, a self-adaptive solution that enhances the Diversity and REAsonability of LLMs' generation strategies. DREAM incorporates an Axiom-Driven Strategy Diversification mechanism to promote varied strategic outcomes and a Sub-Proposition Error Feedback to help LLMs reflect on and correct their proofs. Our contributions include pioneering advancements in LLMs' mathematical reasoning through FOL theorem proving, introducing a novel inference stage solution that improves performance by 1\% to 5\%, and providing a curated dataset of 447 mathematical theorems in Lean4 format for evaluation.

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for modeling long sequences. In light of this, Mamba has attracted attention for maintaining a constant inference size, with empirical evidence demonstrating that it can match Transformer performance in sequence modeling while significantly reducing computational costs. However, an open question remains: can Mamba always bring savings while achieving performance comparable to Transformers? In this paper, we focus on analyzing the expressive ability of Mamba to perform our defined COPY operation and Chain of Thought (CoT) reasoning. First, inspired by the connection between Mamba and linear attention, we show that constant-sized Mamba may struggle to perform COPY operations while Transformers can handle them more easily. However, when the size of Mamba grows linearly with the input sequence length, it can accurately perform COPY, but in this case, Mamba no longer provides overhead savings. Based on this observation, we further analyze Mamba's ability to tackle CoT tasks, which can be described by the Dynamic Programming (DP) problems. Our findings suggest that to solve arbitrary DP problems, the total cost of Mamba is still comparable to standard Transformers. However, similar to efficient Transformers, when facing DP problems with favorable properties such as locality, Mamba can provide savings in overhead. Our experiments on the copy and CoT tasks further demonstrate Mamba’s limitations compared to Transformers in learning these tasks.

Exploring the Limitations of Mamba in COPY and CoT Reasoning

Promoting positive mental health and well-being, especially in adolescents, is a critical yet underexplored area in natural language processing (NLP). Most existing NLP research focuses on clinical therapy or psychological counseling for the general population, which does not adequately address the preventative and growth-oriented needs of adolescents. In this paper, we introduce DeepWell-Adol, a domain-specific Chinese dialogue corpus grounded in positive psychology and coaching, designed to foster adolescents' positive mental health and well-being. To balance the trade-offs between data quality, quantity, and scenario diversity, the corpus comprises two main components: human expert-written seed data (ensuring professional quality) and its mirrored expansion (automatically generated using a two-stage scenario-based augmentation framework). This approach enables large-scale data creation while maintaining domain relevance and reliability. Comprehensive evaluations demonstrate that the corpus meets general standards for psychological dialogue and emotional support, while also showing superior performance across multiple models in promoting positive psychological processes, character strengths, interpersonal relationships, and healthy behaviors. Moreover, the framework proposed for building and evaluating DeepWell-Adol offers a flexible and scalable method for developing domain-specific datasets. It significantly enhances automation and reduces development costs without compromising professional standards—an essential consideration in sensitive areas like adolescent and elderly mental health.

DeepWell-Adol: A Scalable Expert-Based Dialogue Corpus for Adolescent Positive Mental Health and Wellbeing Promotion

Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experiences or online trajectory analysis. However, existing works focus on single-granularity memory derived from dynamic environmental interactions, which are inherently constrained by the quality of the collected experiences. This limitation, in turn, constrain the diversity of knowledge and the flexibility of planning. We propose Coarse-to-Fine Grounded Memory (CFGM), a novel framework that grounds coarse-to-fine memories with LLM, thereby fully leverage them for flexible adaptation to diverse scenarios. CFGM grounds environmental information into coarse-grained focus points to guide experience collection in training tasks, followed by grounding of actionable hybrid-grained tips from each experience. At inference, CFGM retrieves task-relevant experiences and tips to support planning. When facing environmental anomalies, the LLM grounds the current situation into fine-grained key information, enabling flexible self-QA reflection and plan correction. Extensive experiments on AlfWorld, Webshop and ScienceWorld demonstrate that CFGM significantly outperforms competitive baselines and comprehensively optimizes memory-enhanced LLM Agent system.

Coarse-to-Fine Grounded Memory for LLM Agent Planning

Large language models (LLMs) have demonstrated strong performance in solving math problems, and there is growing research on evaluating their robustness. Unlike previous studies that create problem variants by adding perturbations to a single problem, this paper focuses on the interaction between problems. Specifically, we combine two original problems with a logical connection to get a new math problem, and measure the LLMs' performance on it to evaluate its compositional generalization, which is an important and essential reasoning capability in human intelligence. The result of experiments that cover 14 different LLMs shows that even when the mathematical essence remains unchanged, a simple form of combination can significantly reduce the performance of LLMs, revealing the limitation of their generalization ability. Additionally, we propose an automated pipeline with 98.2% accuracy to assist in annotating datasets (1 manual, 2 synthetic). The extensive experiments conducted on these datasets further verify the conclusion and obtain some important findings. Finally, we analyze the impact of factors such as difficulty and length on LLMs performance, offering insights for future research.

Downloads

Next from EMNLP 2025

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Similar lecture

SConU: Selective Conformal Uncertainty in Large Language Models