4 papers
Common-agency Games for Multi-Objective Test-Time Alignment
Baiting Chen, Tong Zhu, Rui Yu +1
Aligning large language models (LLMs) with human preferences is inherently multi-objective: different users and evaluation criteria impose heterogeneous and often conflicting requi…
ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning
Tong Zhu, Baiting Chen, Jin Zhou +3
LLMs often underperform on complex reasoning tasks when relying on a single generation-and-selection pipeline. Inference-time ensemble methods can improve performance by sampling d…
Incentivizing Truthful Language Models via Peer Elicitation Games
Baiting Chen, Tong Zhu, Jiale Han +3
Large Language Models (LLMs) have demonstrated strong generative capabilities but remain prone to inconsistencies and hallucinations. We introduce Peer Elicitation Games (PEG), a t…
Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
Victor Li, Baiting Chen, Yuzhen Mao +2
Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a m…