arXiv AI
Aug 14
Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence
arXiv:2608. 12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling.
Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence
The paper introduces the Wiggle Framework, a unified stress test for assessing epistemic stability in large language model (LLM) judges. It evaluates judge robustness across three dimensions—Mechanical Consistency, Single-turn Conviction, and Multi-turn Persistence—using 9 frontier models on 14 judging tasks related to safety, toxicity, AI writing detection, and political-response evaluation. Results show significant instability, with verdict flips ranging from 25–71% under static pushback and 62–91% when challenged by an adversarial LLM, and highlight that successful pressure often misaligns with ground truth.
Related stories
arXiv AI
Jun 6
Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges
arXiv:2606. 05384v1 Announce Type: new Abstract: LLM-as-judge evaluation is widely used in benchmarking pipelines, where model outputs are compared and ranked using automated evaluators.
arXiv Machine Learning
Oct 8
Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions
The paper introduces Conditional Accuracy Profiling (CAP), a diagnostic framework that breaks down LLM‑judge accuracy into eight deployment conditions covering content sensitivity, robustness, and rationale quality. CAP is benchmark‑agnostic and can be applied directly when annotations are available, via task‑subset proxies, or through controlled augmentation. Applied to seven judges across six benchmarks, CAP reveals that aggregate accuracy masks important differences—for example, judges highly sensitive to omitted qualifications rank poorly on a Hard‑Constructed subset, and Position Robustness is generally stable but can degrade sharply under adversarial stress.
arXiv Machine Learning
Sep 14
Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration
The paper investigates how large language models (LLMs) used as judges in absolute scoring tasks exhibit systematic biases that compromise reliability. It shows that a judge’s task accuracy strongly predicts both its judging accuracy and its directional bias, yet more capable examinee models consistently receive more lenient judgments. To mitigate these biases, the authors propose a calibrated weighted majority voting (WMV) ensemble that estimates judges’ error rates from inter-judge agreement patterns, achieving near-oracle performance without labeled data and improving both accuracy and fairness.
arXiv AI
4d ago
StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as p...
arXiv AI
Sep 10
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.
arXiv AI
Jul 14
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
arXiv:2607. 11871v1 Announce Type: cross Abstract: Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations.
arXiv AI
Aug 26
A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation
The paper introduces a two‑dimensional construct validity framework for evaluating large language models (LLMs) as judges, defining invariance (S) and sensitivity (R) to construct‑preserving and construct‑changing edits. Experiments across seven judges and four domains reveal high invariance (average S = 0.945) but low sensitivity (average R = 0.319), with sensitivity varying by edit type. Audits of public label sets show that surface‑only predictors can reproduce a substantial portion of labels, underscoring that high agreement does not guarantee construct validity.
arXiv AI
Jun 15
The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.
arXiv AI
Jul 10
When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals
arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.
arXiv AI
Oct 9
All Verdicts are Not Equal: Rethinking LLM Judge Reliability
The paper audits the reliability of large language models used as judges in NLP evaluation. It stresses that verdicts can vary across identical replications, change with presentation order, and that even the most deterministic model only agrees with ground truth 51% of the time. The authors introduce the trustworthy verdict rate (T) to quantify reproducibility, order‑invariance, and accuracy, and show that holistic rubric scoring improves trustworthiness more than any single prompting strategy.
arXiv AI
Sep 2
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
The paper "trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories" examines the limitations of outcome-only evaluation for large language model agents. Using a deterministic tool‑using support‑desk environment with a scripted oracle policy and a fault injector, the authors compare five different judging approaches—programmatic rules, outcome‑only, step‑rubric at two model sizes, and a self‑consistency ensemble—on metrics such as detection, step localisation, fault typing, calibration, and cost across 400 trajectories. The study finds that outcome‑only judges miss many silent faults and generate false positives, while step‑rubric judges achieve higher recall with no false alarms but at greater cost, and that none of the judges read the final reply, allowing fabricated promises to evade detection. "whyItMatters":"The findings highlight that current production‑default outcome‑only evaluations can overlook critical failures in agent behavior, underscoring the need for more nuanced, step‑level judging methods to ensure reliable LLM agent performance."