EMNLP

FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline

Parker Seegmiller, Kartik Mehta, Soumya Saha, Chenyang Tao, Shereen Oraby, Arpit Gupta, Tagyoung Chung, Mohit Bansal, Nanyun Peng

机构 * Amazon AGI Foundations（亚马逊人工智能基础研究机构） ； Dartmouth College（达特茅斯学院） ； UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； University of California, Los Angeles（加州大学洛杉矶分校） 纠错

Comments To appear at EMNLP 2025

A Probabilistic Inference Scaling Theory for LLM Self-Correction

Zhe Yang, Yichang Zhang, Yudong Wang, Ziyao Xu, Junyang Lin, Zhifang Sui

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Alibaba Group（阿里巴巴集团） 纠错

Comments EMNLP 2025 Main

XLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering

Keon-Woo Roh, Yeong-Joon Ju, Seong-Whan Lee

机构 * Department of Artificial Intelligence, Korea University（人工智能系，韩国大学） 纠错

Comments Accepted to EMNLP 2025 main conference. 12 pages, 4 figures, 7 tables. Code is available at https://github.com/ro-ko/XLQA

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency

Zhanming Shen, Hao Chen, Yulei Tang, Shaolin Zhu, Wentao Ye, Xiaomeng Hu, Haobo Wang, Gang Chen, Junbo Zhao

机构 * Zhejiang University（浙江大学） ； University of Science and Technology of China（中国科学技术大学） ； Tianjin University（天津大学） 纠错

Comments EMNLP 2025 Main

Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making

Yuanjun Feng, Vivek Choudhary, Yash Raj Shrestha

机构 * University of Lausanne（洛桑大学） ； Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted to EMNLP 2025 (Main Conference)

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

Bohan Yao, Vikas Yadav

机构 * ServiceNow AI ； University of Washington（华盛顿大学） 纠错

Comments Published at EMNLP Findings 2025; 21 pages, 3 figures

HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance

Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark, Abraham Bernstein

Comments EMNLP 2025, 26 pages (9 pages: main paper body)

A Text-Based Recommender System that Leverages Explicit Affective State Preferences

Tonmoy Hasan, Razvan Bunescu

机构 * Department of Computer Science University of North Carolina at Charlotte（计算机科学系北卡罗来纳大学夏洛特分校） 纠错

Comments To appear at EMNLP 2025

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment

Somnath Banerjee, Sayan Layek, Pratyush Chatterjee, Animesh Mukherjee, Rima Hazra

机构 * Indian Institute of Technology Kharagpur（印度理工学院卡里格普尔分校） ； Eindhoven University of Technology（埃因霍温理工大学） 纠错

Comments Accepted at EMNLP 2025

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions

Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song

机构 * Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（计算机科学与工程系，香港科技大学，香港特别行政区，中国） 纠错

Comments Findings of EMNLP 2025