# REA: From Correct LLM Judgments to Safe Decision Delivery

arXiv: https://arxiv.org/abs/2610.17473 · HTML: https://mlsanity.com/paper/2610.17473/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [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)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs](https://mlsanity.com/paper/2509.01790/) (2025)
- [When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output](https://mlsanity.com/paper/2503.24191/) (2025)
- [When the Ruler is Broken: Parsing-Induced Suppression in LLM-Based Security Log Evaluation](https://mlsanity.com/paper/2605.07293/) (2026)
- [AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents](https://mlsanity.com/paper/2605.26596/) (2026)
- [How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring](https://mlsanity.com/paper/2606.25487/) (2026)
- [CheatBench: Measuring Reward Gaming in AI Agents](https://mlsanity.com/paper/2609.36308/) (2026)

## Abstract (arXiv)

Generative safety guards must classify requests correctly and return outputs that applications can parse. Reasoning guards can improve classification accuracy while producing outputs that applications cannot parse. When applications cannot extract a correct prediction, fallback handling can allow harmful requests or block safe ones. We introduce Resolve--Express--Act (REA), a framework that traces judgments through parsing and fallback to application actions. Experiments on classifiers and safety guards show that correct predictions can appear in incorrectly formatted outputs. Parsing the safety verdict preserves the reasoning guard's accuracy advantage, while stricter explanation requirements reject additional correct predictions. Accepting formatting variations recovers most rejected correct predictions. Held-out tests confirm that output requirements and generation limits affect whether correct predictions can be parsed. In our fail-open replay, matching the parser to the output and fixing formatting reduced the fraction of harmful requests allowed despite correct guard judgments from 95.5% to 0%. A fixed-output comparison shows that model-based extraction can preserve guard verdicts, but is not automatically reliable; deterministic normalization already repairs the observed native-format failures. Fallback replay shows that the same correct prediction can lead to different safety actions depending on the parser and fallback policy, including allowing requests the guard correctly identifies as harmful.