565 citations · 773 across the 14 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CL2024
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
David Reber, Sean Richardson, Todd Nief +2
Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they…
cs.CL2024
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
Lin Gui, Cristina Gârbacea, Victor Veitch
This paper concerns the problem of aligning samples from large language models to human preferences using best-of- sampling, where we draw samples, rank them, and return the…