arXiv Machine Learning June 30, 2026 By Matthieu Bou, Nyal Patel, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives

Read the original on arXiv Machine Learning →

arXiv:2510. 06096v3 Announce Type: replace Abstract: The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 30

SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

arXiv:2606. 29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit.

By Aojie Yuan, Yi Nian, Haiyue Zhang, Zijian Su, Yue Zhao

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jul 28

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.

By Yunting Song, Matthew Watson, Peter Grabowski, Jun Qin

llms reinforcement-learning benchmarks safety data-engineering

arXiv Machine Learning

Jun 5

Alignment Risks from Capability-Seeking RL Training

arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.

By Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 30

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.

By Pei-Chi Pan, Yingbin Liang, Sen Lin

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 19

The Autonomy Tax: Defense Training Breaks LLM Agents

arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.

By Shawn Li, Yue Zhao

llms agents benchmarks safety

arXiv AI

Jun 30

Safety from Honesty in a Disinterested AI Predictor

arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.

By Yoshua Bengio, Oliver Richardson, Tom\'a\v{s} Gaven\v{c}iak, Michael Cohen, Rory Svarc, Damiano Fornasiere, Gael Gendron, David Hyland, Aton Kamanda, Adam Oberman, Francis Rhys Ward, Anna Gaven\v{c}iak, Jacob Livingston Slosser, Vincent Mai, Iulian Serban, Joumana Ghosn

agents efficiency safety

Related stories

SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

Alignment Risks from Capability-Seeking RL Training

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

The Autonomy Tax: Defense Training Breaks LLM Agents

Safety from Honesty in a Disinterested AI Predictor