conftrace_

Jianfeng Si

4 papers · 2013–2026 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🏃 Academic Marathon (13) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (11)

Conferences

ACL (2) AAAI (1) EMNLP (1)

Top co-authors

Qing Li (2) Bing Liu (2) Huayi Li (2) Xiangzheng Zhang (2) Zhewen Tan (2) Arjun Mukherjee (2) Lin Sun (2) Huiyan Jin (1) Tong Yang (1) Duohe Ma (1)

Keywords

reinforcement learning (1) safety alignment (1) supervised fine-tuning (1) adversarial prompt generation (1) large language model (1) safety control (1) magic token (1) behavioral switching (1)

Papers

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training AAAI 2026 TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment ACL 2026 Exploiting Social Relations and Sentiment for Stock Prediction EMNLP 2014 Exploiting Topic based Twitter Sentiment for Stock Prediction ACL 2013