CORTEXA
← Browse
arxivcs.CLcs.AI2026-07-09

When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability

Zongyou Yang, Yinghan Hou, Xiaokun Yang

An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed. We treat this evaluator-replacement ambiguity as a measurement-validity problem. Across four judgment datasets, we compare two upgrade paths available in practice: scaling Qwen3 dense judges from 1.7B to 32B parameters and moving across MiniMax M2-M2.7 released APIs. The main pattern is that judge upgrades are not interchangeable: only Qwen3 1.7B to 4B gives a robust adjacent gain, while MiniMax adjacent releases do not. Stronger judges reduce but do not remove position and verbosity bias. Repeated-sample juries add little when errors are correlated. Structured debate can move decisions substantially, but without parser and fallback logs those shifts cannot be attributed to deliberation. We argue that LLM-as-judge reports should include dataset slices, bias probes, error-dependence estimates, and protocol audit trails.

View free PDFSource page

Related papers

arxivcs.CLcs.AIcs.LG2026-07-31

CalibratedRubric: Task-Adaptive Rubric Banks for Open-Ended LLM Evaluation

Mengting Chen, Yanshu Sun, Wanting Liang, Beidi Luan, Rui Sun, Dezhi Chen, et al.

Reliable evaluation of open-ended LLM outputs requires fine-grained rubrics, yet expert curation is costly and difficult to scale. Existing automated pipelines rely on strict judge unanimity and binary variance filters, which cannot distinguish measurable rubrics from informative…

View free PDFSource page
arxivcs.CLcs.AIcs.SE2026-07-30

ORCA-bench: How Ready Are Language Model Agents for Oncall?

Albert Gong, Kyuseong Choi, Abhineet Agarwal, Jason Schechner, Ryan Huang, Raj Agrawal, et al.

Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce…

View free PDFSource page
arxivcs.IRcs.AIcs.CL2026-07-31

RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

Haoran Ling, Yuecheng Li, Zeyu Song, Jing Yao, Shuwen Kang, Chi Lu, et al.

Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes. While LLM-based agents can automate this trial-and-error process, allowing the LLM to both select modification directions and g…

View free PDFSource page
arxivcs.CLcs.AI2026-07-31

ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation

Gaetano Perrone, Simon Pietro Romano

Standard AI-text detection benchmarks compare human-written text against text generated directly by large language models (LLMs). While prior work has shown that rewriting and paraphrasing can degrade detector performance, it remains unclear whether performance measured on this c…

View free PDFSource page