Researcher — paper.dinq.me

作者位次 #10/17ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Hongye Cao · Sijia Jing · Yanming Wang · Ziyue Peng · Zhixin Bai · Zhe Cao · Meng Fang · Fan Feng · JIAHENG LIU · Boyan Wang · Tianpei Yang · Jing Huo · Yang Gao · Fanyu Meng · Xi Yang · Chao Deng · Junlan Feng

安全评测与基准社会与人本OpenReview

作者位次 #3/11ACL 2026Poster· Natural Language Processing

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning

Siyuan Gan · JIAHENG LIU · Boyan Wang · Tianpei Yang · Runqing Miao · Yuyao Zhang · Fanyu Meng · Junlan Feng · Linjian Meng · Jing Huo · Yang Gao

摘要

Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To address this overthinking problem, existing work focuses...

推理强化学习与后训练评测与基准OpenReview 项目页

Boyan Wang

获取完整研究档案

联系方式

2026 顶会论文

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning

常见合作者