Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
Paper • 2510.08146 • Published • 1
Aman Sharma
arcAman07
·
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM
Reasoning authored a paper 4 days ago
The Sequential Edge: Inverse-Entropy Voting Beats Parallel
Self-Consistency at Matched Compute authored a paper 4 days ago
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming LanguagesOrganizations
upvoted 2
papers 5 days ago
upvoted a paper 4 months ago
upvoted an article 8 months ago
Article
System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience
•
24