Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/5ICLR 2026Poster· Reinforcement Learning / Deep RL

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Thanh-Long V. Le · Myeongho Jeon · Kim Vu · Viet Lai · Eunho Yang

强化学习与后训练OpenReview

作者位次 #2/3ICLR 2026Poster· Applications / Language, Speech and Dialog

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

Amirabbas Afzali · Myeongho Jeon · Maria Brbic

对齐与偏好多模态OpenReview

作者位次 #2/7ACL 2026Findings· Findings of ACL

P hase MI : A Motivational Interviewing Dataset for Enhancing Phase Progression in LLM -based Counseling

Jina Kim · Myeongho Jeon · Soohyun Cho · Chae-Gyun Lim · Jongmin Lim · Haewon Min · Eunho Yang

摘要

The growing demand for scalable mental health support has increased interest in AI-based counseling systems grounded in Motivational Interviewing (MI). However, existing MI datasets do not explicitly model the structured progression of MI phases, which is essential for effective and goal-oriented...

评测与基准数据与预训练社会与人本OpenReview 项目页

Myeongho Jeon

获取完整研究档案

联系方式

2026 顶会论文

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

P hase MI : A Motivational Interviewing Dataset for Enhancing Phase Progression in LLM -based Counseling

常见合作者