Paper

Calibrating LLMs with Semantic-level Reward

Unreadunread

AI summary

arXiv:2605. 15588v1 Announce Type: new Abstract: As large language models (LLMs) are deployed in consequential settings such as medical question answering and legal reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use, requiring well-calibrated uncertainty.

Reading status

Priority

About this paper

Authors: Fengfei Yu, Ruijia Niu, Dongxia Wu, Yian Ma, Rose Yu
Released: 2026-05-18 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Calibrating LLMs with Semantic-level Reward overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, rect, correct, wrong, eval, token, line, rate. Source: arxiv cs.CL (NLP).
arXiv: 2605.15588

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Calibrating LLMs with Semantic-level Reward. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.