arXiv AI By Sai Sri Pushpa Jampani, Kshitij Mishra, Asif Ekbal

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment

Read the original on arXiv AI →

AUDITPLAN introduces a plan-then-answer method for safety alignment in language models, where the model first generates a compact structured safety plan before responding. The plan includes a threat label, intended action, and explicit constraints, allowing machine‑checkable auditing while remaining hidden from end users. Training combines supervised fine‑tuning with reinforcement learning using the FAITHGATE reward, which only rewards correct plans, thereby reducing unsafe shortcuts and improving robustness across Qwen model variants.

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 Machine Learning
Aug 27

Training Alignment Auditors via Reinforcement Learning

The paper presents a reinforcement learning approach to enhance large language model (LLM) auditors for alignment tasks. By training policies that investigate target models for hidden behaviors and using an LLM judge to compare investigations, the method improves audit realism and reduces false positives. Experiments show better performance on adversarially fine‑tuned targets and a low false‑positive rate below 1%.

By Paul Rosu, Rowan Wang
arXiv AI
Sep 25

Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning

The paper introduces a protocol for auditing and composing reinforcement‑learning policies using discrete behavioral rules, defining auditability through six testable predicates such as trace integrity and rule coverage. Experiments show that overlapping rule sets do not guarantee behavioral agreement, and that rule‑based fusion often fails to outperform value‑based composition, highlighting limitations in current description layers. The authors provide an evidence‑bounded audit framework and outline future directions for more robust skill composition.

By Liu Hung Ming
arXiv AI
Oct 16

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

PROBE is an algorithm that trains language‑model auditors to probe deployed tool‑using agents for policy violations through realistic, multi‑turn, tool‑mediated dialogue. By framing auditing as a two‑player Markov game and using a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity, PROBE outperforms zero‑shot adversaries in uncovering broader and higher‑yield policy violations. The study compares GRPO, DPO, and GFlowNet optimizations, demonstrating that multi‑turn behavioral auditing is a distinct and necessary axis of agent evaluation, complementing existing capability and safety benchmarks.

By Kshitij Mishra, Abhijith Sharma, Nils Lukas, Salem Lahlou