arXiv Computation and Language October 1, 2026 By Haeun Jang, Yonghyun Jun, Hwanhee Lee

Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs

Read the original on arXiv Computation and Language →

The Flow has not summarised this story yet — read it at arXiv Computation and Language.

arXiv AI

Sep 1

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

arXiv:2608.29464v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness...

By Aryo Pradipta Gema, Neel Rajani, Rohit Saxena, Wai-Chung Kwan, Pasquale Minervini

llms agents 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 AI

Aug 6

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

arXiv:2608. 04735v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models.

By Agatha Duzan, Asa Cooper Stickland

benchmarks safety

arXiv AI

Jul 21

Normalized Rewards for Preference Optimization

arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.

By Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 25

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

arXiv:2510. 04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention.

By Kai Qin, Jiaqi Wu, Jianxiang He, Haoyuan Sun, Yifei Zhao, Xu Wang, Bin Liang, Yongzhe Chang, Cheng Li, Tiantian Zhang, Houde Liu

llms fine-tuning benchmarks safety

arXiv AI

Jun 10

Superficial Beliefs in LLM Decision-Making

arXiv:2606. 11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure.

By Gabriel Freedman, Francesca Toni

llms

One email a morning, machine-written

Related stories

Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

Quantifying and Mitigating Self-Preference Bias of LLM Judges

Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

Normalized Rewards for Preference Optimization

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

Superficial Beliefs in LLM Decision-Making