conftrace_

Jingwen Pu

2 papers · 2026–2026 · 1 conference · across top CS/AI conferences

Conferences

ACL (2)

Top co-authors

Zhaokun Wang (2) Xinyu Zhang (1) Wenyi Li (1) Guangchun Luo (1) Jie Ou (1) Kun She (1) Xinrui Ren (1) Yizhe Wang (1) Hongli Pu (1) Meng Yang (1)

Keywords

reinforcement learning (1) machine unlearning (1) knowledge unlearning (1) controllable generation (1) prompt optimization (1) large language model (1) alignment mechanism (1) entropy-guided decoding (1) inference-time unlearning (1) training-free unlearning (1)

Papers

Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference ACL 2026 CAP: Controllable Alignment Prompting for Unlearning in LLMs ACL 2026