The study analyzes 373,019 judgments from LLM‑scored benchmarks, decomposing variance into system, item, judge, and interaction components via generalizability theory. It finds that with a single judge, generalizability converges to a ceiling determined by the system‑by‑judge variance, which is substantially lower in pairwise preference settings, allowing one judge to suffice. The research also reveals significant biases in presentation order and highlights that many published win‑rate claims fall below the measured floor of the benchmarks.
By Atul Anand
arXiv:2607. 28685v1 Announce Type: new Abstract: Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety.
By Youting Wang, Xiao Han, Dingyan Shang, Yuan Tang, Bowen Liu
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.
By Wenqi Li, Bin Liu, Mindi Ruan, Chuanbo Hu, Minglei Yin, Xin Li
arXiv:2609.07944v1 Announce Type: new
Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recove...
By Yonghong Zhang, Ricardo Correia, Isabel M. Parra, Yong Xie
arXiv:2610.07177v1 Announce Type: cross
Abstract: An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of...
By Gowthamkumar Nandakishore
arXiv:2606. 23767v1 Announce Type: new Abstract: Headline accuracies on the Tuebingen cause-effect pairs are routinely compared across papers even though each is measured under its authors' own protocol -- different pair subsets, weightings, model-selection, and decision rates.
By Wietse Stienstra
arXiv:2608. 15428v1 Announce Type: cross Abstract: Multiple-choice benchmarks are graded on whether a model picks the right option, not on whether it needed the question.
By Volodymyr Ovcharov
arXiv:2610.28522v1 Announce Type: new
Abstract: Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make...
By Xialie Zhuang, Mingcong Lei, Zunhai Su, Ri Liu, Jianjin Li, Peixian Ma, Jia Pan, Ngai Wong, Guanhua Chen, Chuan-Wei Kuo
The article examines how classical test theory reliability statistics misrepresent the performance of large language model (LLM) judges. It shows that internal‑consistency coefficients, the dependability index, and Livingston‑Lewis accuracy each conflate judge error with item design or criterion validity, making it impossible to attribute a single reliability value to the judge alone. The authors argue that such misattribution can influence deployment decisions and documentation.
By Louis Yiven Zhu
The article examines how classical test theory statistics—Kuder‑Richardson coefficient, dependability index, and Livingston‑Lewis accuracy—can mislead when applied to large language model (LLM) judges that are evaluated with a single prompt and no gold labels. Using Claude Haiku 4.5 on 210 short‑answer items, the authors show that these metrics fail to isolate the judge’s performance because the judge’s single administration provides no variance component. They argue that reliable statements about an LLM judge require gold labels or varied scorer facets, and that bank design heavily influences reliability estimates.
By Louis Yiven Zhu
The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.
By Jiapeng Li
arXiv:2607. 02104v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise.
By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao