---
title: "When Does Better Confidence Improve a Knowledge-Graph Audit?"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05877v1"
permalink: "https://feed.astralor.com/items/itm_7b7fb33fde987ec018cd1a41"
published: "2026-11-04T03:12:37.000Z"
score: 57
channel: "ai"
tags: ["LLM","推理效率","When Does Better","Confidence Improve","Knowledge-Graph Audit","Confidence","LLM-built","Modelling"]
---

# When Does Better Confidence Improve a Knowledge-Graph Audit?

## At a glance

Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity…

## Key points

- Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit.
- We study this gap through repairability, selection headroom and label validity.
- Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $Δ^{\mathrm{cl}}$.

## Full text

Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $Δ^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. On the held-out cross-document graphs, an error-rate $\times$ fan-out queue leaves 3.98-4.74 percentage points more errors than a joint model with the same actions. By comparison, opening shared actions for that joint planner reduces residual errors by 0.89-1.43 points relative to its own fact-only plans, in point estimates. Equivalence between joint and independent-block models remains inconclusive. Generic LLM verification improves three of four model-budget configurations on each held-out set. LLM adjudication identifies possible benchmark omissions.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_7b7fb33fde987ec018cd1a41