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.
By Ilija Subasic, Brett Levert, Andrew Rabinovich, Sajjad Pakdamansavoji, Zhao Chen
The paper reproduces five factuality alignment methods for large language models—three on‑policy RL approaches (PPO, GRPO, Dr.GRPO) and two offline preference optimization methods (DPO, KTO)—using a common benchmark and evaluation metrics. None of the methods consistently outperforms the base model, and the rewards appear to favor format, length, or brevity rather than factuality or relevance. The study also highlights problems with current evaluation practices, noting that metrics and benchmarks often fail to measure prompt relevance and rely on fragile LLM judges and retrieval for verification.
arXiv:2610.18415v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment st...
By Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand
The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.
By Ej Zhou, Lucas Resck, Zheng Hui, Anna Korhonen
arXiv:2602.02219v3 Announce Type: replace
Abstract: Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examin...
By Yuzheng Xu, Tosho Hirasawa, Tadashi Kozuno, Yoshitaka Ushiku
arXiv:2609.14795v1 Announce Type: cross
Abstract: There is a tradeoff in machine translation meta-evaluation between prioritizing alignment with adequacy versus fluency. The balance depends on the co...
By Behzad Shayegh, Niloofar Kazemi
arXiv:2605. 28969v2 Announce Type: replace-cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user.
By Aarik Gulaya
arXiv:2605.28313v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality o...
By Nicol\'as Benjam\'in Ocampo, Agnes Paullate Nyiranziza, Davide Ceolin
arXiv:2606. 13221v2 Announce Type: replace Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale.
By Bora Kargi, David Salinas
VALCON introduces a role-driven framework to benchmark and improve value consistency in large language models (LLMs) by evaluating how well an LLM’s generative outputs align with its evaluative judgments when the same model alternates between generator and evaluator roles. The framework creates three benchmark suites—VAB-Consistency, VAB-Boundary, and VAB-Challenge—using dual-role variation to expose hidden value discrepancies. Experiments across 28 LLMs reveal widespread cross-role inconsistency, and mechanistic probing identifies a role-dependent representational decoupling; a representation-directed intervention is then proposed to mitigate these failures, establishing value consistency as a distinct alignment dimension.
By Junru Wu, Jingting Zheng, Yuqi Ren, Deyi Xiong
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
By Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao