arXiv Machine Learning

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

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.

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

Hugging Face Trending Papers

Jun 28

Safety from Honesty in a Disinterested AI Predictor

As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.

agents efficiency safety

arXiv AI

Jul 3

Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence

arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.

By Niklas Herbster, Martin Zborowski, Alberto Tosato, Gauthier Gidel, Tommaso Tosato

llms agents fine-tuning benchmarks 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

arXiv AI

Jun 30

EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures

arXiv:2606. 30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify.

By Bu\u{g}ra Alperen Ulu{\i}rmak, Rifat Kurban

llms benchmarks safety

arXiv Machine Learning

Jun 5

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents

arXiv:2606. 05263v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks.

By Renwei Meng

agents reinforcement-learning

arXiv AI

Jul 21

Zero Hallucination, by Construction: Hallucination-Aware Layered Oversight for Trustworthy Enterprise AI

arXiv:2607. 17883v1 Announce Type: cross Abstract: Enterprises will not deploy AI agents they cannot trust, and the most-cited reason for distrust is hallucination: confident, fluent output that is simply not true.

By Bogdan Raduta, Horia Velicu, Alexandru Preda, Serban Chiricescu

llms agents safety

Related stories