arXiv AI June 24, 2026 By Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Simon Fu, Narmeen Oozeer

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

arXiv:2509. 03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models.

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.

arXiv Computation and Language

Sep 1

Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation

arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...

By Alessio Galatolo, Meriem Beloucif

llms safety

arXiv AI

Jun 2

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.

By Daniel Fein, Max Lamparth, Violet Xiang, Mykel J. Kochenderfer, Nick Haber

llms benchmarks safety

arXiv AI

Jun 3

Quantifying and Mitigating Self-Preference Bias of LLM Judges

arXiv:2604. 22891v4 Announce Type: replace-cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on.

By Jinming Yang, Zheng Hu, Chuxian Qiu, Zhenyu Deng, Xinshan Jiao, Tao Zhou

llms benchmarks safety

arXiv Machine Learning

Sep 23

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors

arXiv:2504.20106v4 Announce Type: replace Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessiv...

By Ren-Wei Liang, Chin-Ting Hsu, Chan-Hung Yu, Saransh Agrawal, Shih-Cheng Huang, Chieh-Yen Lin, Shang-Tse Chen, Kuan-Hao Huang, Shao-Hua Sun

llms reinforcement-learning safety

arXiv AI

3d ago

Optimal Design for Active Preference Learning with Biased LLM Judges

arXiv:2609.38860v1 Announce Type: cross Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference lear...

By Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang

llms safety

arXiv AI

Sep 3

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations

CroCo introduces cross‑lingual contrastive preference tuning on self‑generations, extending prior English‑only methods to 14 high‑ and low‑resource languages. A reward model trained solely on English preferences, applied to a multilingual base, yields effective within‑language rankings and improves performance in both monolingual and multilingual settings without catastrophic forgetting. The approach requires on‑policy data; off‑policy responses and online preference optimization offer limited gains, yet on structured tasks CroCo matches or surpasses the base model in most languages, and on open‑ended generation it wins 28/30 judge evaluations across 15 languages.

By Mike Zhang, Ali Basirat, Desmond Elliott

llms reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

Quantifying and Mitigating Self-Preference Bias of LLM Judges

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors

Optimal Design for Active Preference Learning with Biased LLM Judges

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations