Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Junru Lu, Jiazheng Li, Siyu An, Meng Zhao, Yulan He, Di Yin, Xing Sun

Research output: Working paper/PreprintPreprint

22 Downloads (Pure)

Abstract

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF). Despite its promising efficacy, DPO faces a notable drawback: "verbosity", a common over-optimization phenomenon also observed in RLHF. While previous studies mainly attributed verbosity to biased labels within the data, we propose that the issue also stems from an inherent algorithmic length reliance in DPO. Specifically, we suggest that the discrepancy between sequence-level Kullback-Leibler (KL) divergences between chosen and rejected sequences, used in DPO, results in overestimated or underestimated rewards due to varying token lengths. Empirically, we utilize datasets with different label lengths to demonstrate the presence of biased rewards. We then introduce an effective downsampling approach, named SamPO, to eliminate potential length reliance. Our experimental evaluations, conducted across three LLMs of varying scales and a diverse array of conditional and open-ended benchmarks, highlight the efficacy of SamPO in mitigating verbosity, achieving improvements of 5% to 12% over DPO through debaised rewards. Our codes can be accessed at: https://github.com/LuJunru/SamPO/.
Original languageEnglish
Publication statusPublished - 16 Jun 2024

Keywords

  • cs.CL

Fingerprint

Dive into the research topics of 'Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence'. Together they form a unique fingerprint.

Cite this