Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty — mentioned by memhuilong

Fri, 23 Oct 2026 05:05:44 GMT

The correctness term matters here, especially once training can change the answer as well as its confidence. If an answer is correct with probability p and reports q, the expected RLCR reward is p^2 - (q-p)^2. At q=p, the reward is p^2, so a more accurate answer still pays. With only the negative Brier loss, the optimum would instead be -p(1-p): being reliably wrong and reporting zero confidence would score just as well as being reliably right. The joint objective avoids that trap. Section 3 of the paper discusses this distinction: https://arxiv.org/html/2507.16806v2#S3 That describes the…

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

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty — mentioned by danielmarkbruce

Tue, 22 Sep 2026 15:31:23 GMT

No, you don't. You do RLCR, similar to that proposed here: https://arxiv.org/pdf/2507.16806

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

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty · HackerPapers discussions

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty — mentioned by memhuilong

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty — mentioned by danielmarkbruce