跳到正文
arXiv cs.AI· Khushal Sethi·· 56 分钟前AI 评分49

一致性不等于纠错:分离 LLM Agent 的置信度、弃答与恢复

Consistency Is Not Correction: Separating Confidence, Abstention, and Recovery in LLM Agents

AI 导读

Khushal Sethi 等人在 arXiv 论文中指出,LLM Agent 控制器的置信度信号用于排序答案、选择性弃答和纠错是三种不同能力,并给出纠错效用的精确分解:门控可带来的正确改写受初始错误数上限约束,低于配对检验所需数量时实验注定无法得到显著正结果。

正文 · 原文

View PDF HTML (experimental)

Abstract:A controller that resamples an answer, escalates to a larger model, or abstains is usually justified by a confidence signal. Three claims about such a signal do not follow from one another: it ranks answers (discrimination), it supports withholding some of them (selective prediction), and it changes an answer for the better (correction utility). We give an exact decomposition of the third into gated recoveries minus gated harms, which bounds whether a comparison can succeed before it is run: a gate that only replaces a proposal can act only where the base policy was already wrong, so the initial error count caps the discordant pairs any correct gate can produce. When that cap falls below the count a paired test needs, the experiment cannot return a positive result for a working mechanism, nor distinguish one from a gate that never fired. We measure all three targets on two model scales and find the bound binds. In a small-model suite a perturbation-agreement verifier reaches within-policy AUROC 0.990 (95% interval [0.95, 1.00]) while every episode outcome matches single-sample decoding at 4.32 times the call count. In a controlled 840-episode study no verifier replaced the proposal on any of the 60 GSM8K decisions, so that comparison tested nothing; the entire GSM8K gain across six controllers is one task, and it is the task whose identical temperature-zero repeats disagreed, making it the one answer the service does not reproduce. On the diagnostic set the gate could reach four errors while the test needed six, so even a perfect gate had no significant result available. We report two checks that would have caught this before any budget was spent, and show that tie handling in rankings, tied selection cutoffs, and unequal output limits each move a headline number in the same dataset. The binding constraint on this literature is measurement resolution, not the choice of signal.
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as: arXiv:2611.21651 [cs.CL]
  (or arXiv:2611.21651v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.21651

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Khushal Sethi [view email]
[v1] Thu, 15 Oct 2026 05:55:30 UTC (61 KB)

来源:arXiv cs.AI · arxiv.org