arXiv AI October 31, 2026 By Ilija Subasic, Brett Levert, Andrew Rabinovich, Sajjad Pakdamansavoji, Zhao Chen

Prompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing

The paper introduces the "Prompt Lottery" phenomenon, where paraphrastic rephrasings of judge prompts in LLM-as-a-Judge (LLMaJ) lead to inconsistent judgments and can even reverse model rankings. A large-scale study across various tasks, judge families, and model backbones demonstrates that these prompt variations significantly alter evaluation outcomes. A user study shows that LLMaJ judges are 6–9 times more sensitive to prompt rephrasings than humans, and that aggregating multiple prompts improves robustness by focusing on consistent judgments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Sep 30

PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators

PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.

By Cheng Chang, Yining Mao, Peng Qi

llms agents safety

arXiv AI

Jul 21

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.

By Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe, C\'eline Hudelot, Pierre Colombo

llms

arXiv AI

Jun 26

Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.

By Sangwoo Cho, Kushal Chawla, Pengshan Cai, Zefang Liu, Chenyang Zhu, Shi-Xiong Zhang, Sambit Sahu

llms nlp benchmarks

arXiv AI

Jul 10

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

arXiv:2601. 22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design.

By Zhuochun Li, Yong Zhang, Ming Li, Yuelyu Ji, Yiming Zeng, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao, Daqing He

llms benchmarks

arXiv Machine Learning

Oct 23

Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness

The study investigates how different prompting strategies affect large language model (LLM) judges across multiple languages and tasks. Using a benchmark of 9 prompting strategies, 4 open-weight judges, 27 languages, and 4 tasks, the authors collected over 1 million pointwise scores validated against human judgments. Results show that prompting effectiveness is highly dependent on the judge model, can reverse direction across judges, and becomes less stable in low‑resource languages, indicating that prompt choice must be tailored to the specific evaluation setting.

By Asal Mehrabi, Mohammad Aliannejadi, Clemencia Siro

llms benchmarks

arXiv AI

Jul 17

Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation

arXiv:2607. 14109v1 Announce Type: cross Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding.

By Inder Preet, Shuxin Lin, Dhaval Patel

llms nlp benchmarks

One email a morning, machine-written

Related stories

PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness

Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation