大模型对齐与安全

This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs

Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI

Comments 35 pages, 9 figures, 16 tables

Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model

Fabio Michele Russo, Carlo Metta, Anna Monreale, Salvatore Rinzivillo, Fabio Pinelli

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI、cs.LG

Journal ref Discovery Science 2024, Springer Nature

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages

Amir Hossein Kargaran, François Yvon, Hinrich Schütze

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2024

Automatic database description generation for Text-to-SQL

Yingqi Gao, Zhiling Luo

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

Arth Shukla, Stone Tao, Hao Su

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

AutoBencher: Towards Declarative Benchmark Construction

Xiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu, Yifan Mai, Percy Liang, Tatsunori Hashimoto

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.LG

Comments Accepted for publication at ICLR 2025

Do Large Language Models Align with Core Mental Health Counseling Competencies?

Viet Cuong Nguyen, Mohammad Taher, Dongwan Hong, Vinicius Konkolics Possobom, Vibha Thirunellayi Gopalakrishnan, Ekta Raj, Zihang Li, Heather J. Soled, Michael L. Birnbaum, Srijan Kumar, Munmun De Choudhury

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 10 Pages, Accepted to Findings of NAACL 2025

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

Yi Liu, Changran Xu, Yunhao Zhou, Zeju Li, Qiang Xu

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments ICLR 2025 Spotlight

Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis

Brian Y. Lim, Joseph P. Cahaly, Chester Y. F. Sng, Adam Chew

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments CHI 2025

Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks

Rylan Schaeffer, Punit Singh Koura, Binh Tang, Ranjan Subramanian, Aaditya K Singh, Todor Mihaylov, Prajjwal Bhargava, Lovish Madaan, Niladri S. Chatterji, Vedanuj Goswami, Sergey Edunov, Dieuwke Hupkes, Sanmi Koyejo, Sharan Narang

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.LG

Language Models' Factuality Depends on the Language of Inquiry

Tushar Aggarwal, Kumar Tanmay, Ayush Agrawal, Kumar Ayush, Hamid Palangi, Paul Pu Liang

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.CL、cs.AI

Accelerating Unbiased LLM Evaluation via Synthetic Feedback

Zhaoyi Zhou, Yuda Song, Andrea Zanette

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.LG

Guiding Through Complexity: What Makes Good Supervision for Hard Math Reasoning Tasks?

Xuan He, Da Yin, Nanyun Peng

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments NAACL 2025 Main

Socratic: Enhancing Human Teamwork via AI-enabled Coaching

Sangwon Seo, Bing Han, Rayan E. Harari, Roger D. Dias, Marco A. Zenati, Eduardo Salas, Vaibhav Unhelkar

专题命中 安全评测 ：trustworthy(abstract)；分类 cs.AI、cs.LG

Comments Extended version of an identically-titled paper accepted at AAMAS 2025

Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models

Srishti Yadav, Zhi Zhang, Daniel Hershcovich, Ekaterina Shutova

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Journal ref NAACL 2025

Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator

Frederic Kirstein, Terry Ruas, Bela Gipp

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Journal ref COLING 2025 Industry Track

A Closer Look at System Prompt Robustness

Norman Mu, Jonathan Lu, Michael Lavery, David Wagner

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI

Comments Artifacts: https://github.com/normster/RealGuardrails

What's in a Query: Polarity-Aware Distribution-Based Fair Ranking

Aparna Balagopalan, Kai Wang, Olawale Salaudeen, Asia Biega, Marzyeh Ghassemi

专题命中 安全评测 ：safety(abstract)；分类 cs.CY、cs.LG

Comments Published in WWW 2025

Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations

Oualid Bougzime, Samir Jabbar, Christophe Cruz, Frédéric Demoly

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments 54 pages, 7 figures

Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study

Anneketh Vij, Changhao Liu, Rahul Anil Nair, Theodore Eugene Ho, Edward Shi, Ayan Bhowmick

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, 10 figures,14 tables

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Evaluating improvements on using Large Language Models (LLMs) for property extraction in the Open Research Knowledge Graph (ORKG)

Sandra Schaftner

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Identifying relevant indicators for monitoring a National Artificial Intelligence Strategy

Renata Pelissari, Ricardo Suyama, Leonardo Tomazeli Duarte, Henrique Sá Earp

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.CY

LegalScore: Development of a Benchmark for Evaluating AI Models in Legal Career Exams in Brazil

Roberto Caparroz, Marcelo Roitman, Beatriz G. Chow, Caroline Giusti, Larissa Torhacs, Pedro A. Sola, João H. M. Diogo, Luiza Balby, Carolina D. L. Vasconcelos, Leonardo R. Caparroz, Albano P. Franco

专题命中 安全评测 ：alignment(abstract)；分类 cs.AI、cs.CY

Comments Main article 25 pages, Appendices from page 26

Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluation

Zhiyin Tan, Jennifer D'Souza

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments accepted by IRCDL 2025

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models

Sina Tayebati, Divake Kumar, Nastaran Darabi, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi

专题命中 安全评测 ：safety(abstract)；分类 cs.AI、cs.LG

DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models

Utkarsh Tiwari, Aryan Seth, Adi Mukherjee, Kaavya Mer, Kavish, Dhruv Kumar

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.LG

Knowledge Graph Guided Evaluation of Abstention Techniques

Kinshuk Vasisht, Navreet Kaur, Danish Pruthi

专题命中 安全评测 ：safety(abstract)；分类 cs.CL、cs.AI

Comments Accepted to NAACL 2025

Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis

Yiyi Chen, Qiongxiu Li, Russa Biswas, Johannes Bjerva

专题命中 安全评测 ：alignment(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, 15 figures, 14 tables