2 papers
cs.LG2025
Selective Matching Losses -- Not All Scores Are Created Equal
Gil I. Shamir, Manfred K. Warmuth
Learning systems match predicted scores to observations over some domain. Often, it is critical to produce accurate predictions in some subset (or region) of the domain, yet less i…
cs.LG2024
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo +15
The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from…