3

Mitigating Agreement Bias in LLMs via Contradictory-Knowledge Prompt Triads and Reinforcement Training
Measures and mitigates sycophancy in LLMs using contradictory-knowledge prompt triads and reinforcement training, building on a post-training-stage audit of open-recipe models. In preparation.
Chao Péter Yang
FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation
A governed multi-agent framework that embeds structured dissent into financial AI committees via the Disagree-or-Commit protocol, improving reasoning accuracy and risk awareness over consensus-seeking baselines.
Chao Péter Yang, Zixiao Tan, Kaisen Yao, Ziyu Zhou, Eleanor Jiang, Michael Wu
PDF Source Document
Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts
Controllable AI composition from injected motif prompts, building on ProGress to let users steer structured symbolic music generation. Submitted to NeurIPS 2026 (Creative AI Track).
Chao Péter Yang, Cynthia Rudin, Simon Mak, Yue Jiang, Stephen Ni-Hahn
SchenkerLink: Human-in-the-Loop Hierarchical Music Analysis with Uncertainty-Aware Graph Link Prediction
SchenkerLink introduces an uncertainty-aware, human-in-the-loop framework for hierarchical music analysis with graph link prediction, supporting interpretable, collaborative analysis. Under review for KDD 2027.
Stephen Ni-Hahn, Jerry Zhu, Chao Péter Yang, Cynthia Rudin, Simon Mak, Yue Jiang