7 papers · 1 filter
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Ruizhe Shi, Minhak Song, Runlong Zhou +3
We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO).…
Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
Shulun Chen, Runlong Zhou, Zihan Zhang +2
Aligning large language models (LLMs) with human preferences has proven effective for enhancing model capabilities, yet standard preference modeling using the Bradley-Terry model a…
The Crucial Role of Samplers in Online Direct Preference Optimization
Ruizhe Shi, Runlong Zhou, Simon S. Du
Direct Preference Optimization (DPO) has emerged as a stable, scalable, and efficient solution for language model alignment. Despite its empirical success, the optimization propert…
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Ruizhe Shi, Yuyao Liu, Yanjie Ze +2
Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore,…
Reflect-RL: Two-Player Online RL Fine-Tuning for LMs
Runlong Zhou, Simon S. Du, Beibin Li
As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These task…