Reasoning Models Better Express Their Confidence — mentioned by martianlantern

Mon, 18 Aug 2025 05:09:54 GMT

Hey, really cool work love the idea of focusing on key decision points. I was curious though since confidence can be non monotonic during CoT[1], how does binary search handle cases where there are multiple ups and downs in confidence? It seems like there might be more than one "pivotal" token, so I wonder if there's a plan to support multi-token pivots or use a different approach than binary search? [1] - https://arxiv.org/abs/2505.14489

Paper and discussion history. A mention is not an endorsement.

Reasoning Models Better Express Their Confidence · HackerPapers discussions

Reasoning Models Better Express Their Confidence — mentioned by martianlantern