Debiasing as a Measurement Intervention: Calibrated Ties and Resolution Loss in LLM-as-a-Judge Evaluation

• URL: http://arxiv.org/abs/2609.12439v1
• Date: Fri, 11 Sep 2026 04:59:10 GMT
• Title: Debiasing as a Measurement Intervention: Calibrated Ties and Resolution Loss in LLM-as-a-Judge Evaluation
• Abstract summary: LLM-as-a-judge protocols are commonly debiased by instructing judges to ignore presentation cues.<n>We show that this intervention can suppress bias while damaging the resolution of the measurement instrument.<n>We introduce TraceJudgeBench, a diagnostic benchmark for auditing citation-like artifacts in RAG and agent-workflow evaluation.
• Score: 8.796833451421493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-as-a-judge protocols are commonly debiased by instructing judges to ignore presentation cues such as citation formatting, source labels, and evidence-display style. We show that this intervention can suppress bias while damaging the resolution of the measurement instrument. We introduce TraceJudgeBench, a diagnostic benchmark for auditing citation-like artifacts in RAG and agent-workflow evaluation, covering content-equivalent pairs, citation ablations, correctness conflicts, human-validated soft and moderate quality gaps, prompt-strength ladders, decoupled judging, and a controlled workflow-ranking probe. Across GPT-5.5, Claude Sonnet 4.6, and DeepSeek V4-Flash, stronger anti-citation prompts reduce worse-cited wins from up to 50.5% to 0%; yet some operating points already convert validated moderate-gap decisions into Tie before the strict stress-test endpoint, while correctness-conflict accuracy remains at or above 93.0%. A second, 50-pair FinQA moderate-gap construction reproduces the qualitative frontier, and open-weight Qwen2.5-14B-Instruct-AWQ and Gemma-3-12B-IT runs reproduce the central HotpotQA frontier. TRACE-style decoupling recovers 96.5-100.0% better-plain resolution across the reported settings. Human validation separates three meanings of Tie: correct equivalence Tie, calibrated soft-boundary Tie, and resolution-destroying Tie on validated quality gaps. We frame debiasing as a measurement intervention whose bias suppression, resolution retention, Tie cost, and protocol cost must be reported jointly. The supplementary artifact contains benchmark splits, prompts, raw judge outputs, validation summaries, and analysis.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models [49.47300047353726]
  We introduce MemToC, a benchmark for post-tool-return arbitration with executable tools.<n>MemToC comprises 6,504 evaluation episodes constructed from 542 quality-controlled factual questions.<n>Across five open-weight 7-9B models, tool returns strongly dominate elicited closed-book answers.
  arXiv  Detail & Related papers  (2026-08-26T18:22:03Z)
• Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models [7.714704554667688]
  Large Language Models (LLMs) increasingly support decision-making in high-stakes domains.<n>LLMs often hallucinate and express confidence that is misaligned with factual correctness.<n>We study claim-level confidence calibration as a decision-relevant uncertainty signal.
  arXiv  Detail & Related papers  (2026-08-23T16:09:54Z)
• Guaranteed Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group [0.0]
  A multimodal system may begin inference holding only some of its inputs and may acquire the rest at a cost.<n>We characterize when pattern-conditional guarantees remain valid and give two finite-sample constructions.<n>A counterexample shows that a guarantee proved for a calibration-independent grouping map need not transfer once the policy makes the terminal group calibration-dependent.
  arXiv  Detail & Related papers  (2026-08-16T04:19:31Z)
• Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM Reasoning [5.634990956257954]
  Large language models produce fluent but often incorrect multi-step reasoning, and naive correction methods risk degrading already-correct answers.<n>We introduce Denoising Iterative Self-Correction (DISC), a test-time procedure that treats verification question outputs as noisy measurements of where a solution may be corrupted.<n>A binary judgment gate controls correction precision by blocking rewrites that would damage already-correct answers while the verifier and corrector together repair errors.
  arXiv  Detail & Related papers  (2026-06-19T20:23:14Z)
• Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG [6.113159481005088]
  We introduce FORCEBENCH, a contrastive stress test for evidence-force calibration.<n>Each item holds a cited passage fixed and pairs an evidence-calibrated claim with a localized force-raised variant.<n>Headline experiments use a fixed, locality-filtered 198-pair evaluation set.
  arXiv  Detail & Related papers  (2026-05-27T06:47:44Z)
• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning [8.024041325202612]
  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths.<n>We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty.<n>Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control.
  arXiv  Detail & Related papers  (2026-05-13T20:33:59Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam [63.84155758655084]
  Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models.<n>We introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy.<n>We evaluate seven state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points.
  arXiv  Detail & Related papers  (2026-02-15T02:50:15Z)
• LLMs Can Patch Up Missing Relevance Judgments in Evaluation [56.51461892988846]
  We use large language models (LLMs) to automatically label unjudged documents. We simulate scenarios with varying degrees of holes by randomly dropping relevant documents from the relevance judgment in TREC DL tracks. Our method achieves a Kendall tau correlation of 0.87 and 0.92 on an average for Vicuna-7B and GPT-3.5 Turbo respectively.
  arXiv  Detail & Related papers  (2024-05-08T00:32:19Z)
• Beyond calibration: estimating the grouping loss of modern neural networks [68.8204255655161]
  Proper scoring rule theory shows that given the calibration loss, the missing piece to characterize individual errors is the grouping loss. We show that modern neural network architectures in vision and NLP exhibit grouping loss, notably in distribution shifts settings.
  arXiv  Detail & Related papers  (2022-10-28T07:04:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.