# AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment

arXiv: https://arxiv.org/abs/2609.19325 · HTML: https://mlsanity.com/paper/2609.19325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [PLeak: Prompt Leaking Attacks against Large Language Model Applications](https://mlsanity.com/paper/2405.06823/) (2024)
- [InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance](https://mlsanity.com/paper/2401.11206/) (2024)
- [Stepwise Alignment for Constrained Language Model Policy Optimization](https://mlsanity.com/paper/2404.11049/) (2024)
- [Safety Alignment Can Be Not Superficial With Explicit Safety Signals](https://mlsanity.com/paper/2505.17072/) (2025)
- [A Multi-Level Framework for the AI Alignment Problem](https://mlsanity.com/paper/2301.03740/) (2023)
- [Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments](https://mlsanity.com/paper/2511.13788/) (2025)
- [AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?](https://mlsanity.com/paper/2510.11235/) (2025)

## Abstract (arXiv)

Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requests and polished but unfaithful safety rationales that do not actually constrain the answer. We propose AUDITPLAN, a single-model plan-then-answer approach where the model first emits a compact structured safety plan and then answers conditioned on it. The plan records a threat label, intended action, and explicit constraints, enabling machine-checkable auditing while remaining hidden from users at deployment. We train this behavior with supervised fine-tuning followed by reinforcement learning with FAITHGATE, a reward-gating objective that grants answer reward only when the safety plan is correct. This discourages safe-looking but unfaithful behavior and promotes tighter plan-answer coupling. Across Qwen backbones, AUDITPLAN improves both robustness and auditability: on Qwen2.5-3B-Instruct, FAITHGATE reduces ASR from 24.0% to 11.6%, LSR from 1.0% to 0.36%, and over-refusal from 11.0% to 2.0%, outperforming answer-only RL, free-form explanation, and weighted-sum structured rewards. Similar trends hold for Qwen2.5-1.5B-Instruct. Larger-model confirmation runs on Qwen-3-4B-Instruct and Qwen2.5-7B-Instruct preserve the same trend suggesting that explicit internal commitments can make safety alignment more faithful, robust, and auditable.