conftrace_

Xinmiao Huang

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

Conferences

ACL (2)

Top co-authors

Xiaowei Huang (2) Yi Dong (2) Jinwei Hu (1) Zhuoyun Li (1) Youcheng Sun (1) Boxuan Wang (1)

Keywords

large language model (1) semantic entropy (1) belief manipulation (1) cognitive collusion attack (1) generative montage (1) multi-agent collusion (1) adversarial debate (1) alignment score (1)

Papers

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage ACL 2026 Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models ACL 2026