Hugging Face Trending Papers June 3, 2026

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

Read the original on Hugging Face Trending Papers →

Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is largely present before any targeted training: prompted few-shot, a base model already predicts an external judge's multi-attribute quality scores on open-ended responses well above chance across three benchmarks.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 29

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

arXiv:2606. 28050v1 Announce Type: cross Abstract: LLM-as-a-Judge and self-evaluation pipelines implicitly assume that evaluation is easier than generation.

By Sambaran Bandyopadhyay

llms fine-tuning benchmarks safety

arXiv AI

Jul 23

Self-Preference Bias in Rubric-Based Evaluation of Large Language Models

arXiv:2604. 06996v2 Announce Type: replace-cross Abstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs.

By Jos\'e Pombal, Ricardo Rei, Andr\'e F. T. Martins

llms benchmarks safety

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

arXiv AI

Jul 23

Co-Evolving LLM Evaluators and Policies via DynamicRubric

arXiv:2607. 20083v1 Announce Type: cross Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models.

By Beining Wang, Weihang Su, Hongtao Tian, Hao Kong, Tao Yang, Ting Yao, Qingyi Pan, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu

llms reinforcement-learning

arXiv AI

Aug 12

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.

By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 18

Self-CTRL: Self-Consistency Training with Reinforcement Learning

arXiv:2606. 18327v1 Announce Type: cross Abstract: Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users.

By Itamar Pres, Laura Ruis, Melat Ghebreselassie, Belinda Z. Li, Jacob Andreas

llms reinforcement-learning safety

Related stories

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

Self-Preference Bias in Rubric-Based Evaluation of Large Language Models

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

Co-Evolving LLM Evaluators and Policies via DynamicRubric

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

Self-CTRL: Self-Consistency Training with Reinforcement Learning