hypothesis-ranking

Tag

Cards List
#hypothesis-ranking

Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking

arXiv cs.AI · 2026-08-19 Cached

This paper proposes a logit-based energy scoring method for evaluating scientific hypotheses using large language models, which outperforms prompted LLM-as-judge methods in hypothesis ranking tasks.

0 favorites 0 likes
← Back to home

Submit Feedback