all AI news
Bayesian Reward Models for LLM Alignment
Feb. 21, 2024, 5:42 a.m. | Adam X. Yang, Maxime Robeyns, Thomas Coste, Jun Wang, Haitham Bou-Ammar, Laurence Aitchison
cs.LG updates on arXiv.org arxiv.org
Abstract: To ensure that large language model (LLM) responses are helpful and non-toxic, we usually fine-tune a reward model on human preference data. We then select policy responses with high rewards (best-of-n sampling) or further optimize the policy to produce responses with high rewards (reinforcement learning from human feedback). However, this process is vulnerable to reward overoptimization or hacking, in which the responses selected have high rewards due to errors in the reward model rather than …
abstract alignment arxiv bayesian cs.lg data feedback human human feedback language language model large language large language model llm policy reinforcement reinforcement learning responses reward model sampling type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US