26 citations · 81 across the 18 of their papers we have counts for
3 papers · 1 filter
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
Benjamin Feuer, Micah Goldblum, Teresa Datta +5
The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior…
Large Language Models Must Be Taught to Know What They Don't Know
Sanyam Kapoor, Nate Gruver, Manley Roberts +7
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is s…
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
Arka Pal, Deep Karkhanis, Samuel Dooley +3
Direct Preference Optimisation (DPO) is effective at significantly improving the performance of large language models (LLMs) on downstream tasks such as reasoning, summarisation, a…