# AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models

arXiv: https://arxiv.org/abs/2508.06124 · HTML: https://mlsanity.com/paper/2508.06124/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models](https://mlsanity.com/paper/2501.03124/) (2025)
- [Process Reward Models for LLM Agents: Practical Framework and Directions](https://mlsanity.com/paper/2502.10325/) (2025)
- [Evaluating Mathematical Reasoning Beyond Accuracy](https://mlsanity.com/paper/2404.05692/) (2024)
- [RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability](https://mlsanity.com/paper/2504.10081/) (2025)
- [R-PRM: Reasoning-Driven Process Reward Modeling](https://mlsanity.com/paper/2503.21295/) (2025)
- [Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements](https://mlsanity.com/paper/2410.08968/) (2024)
- [How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries](https://mlsanity.com/paper/2402.15302/) (2024)
- [AURORA:Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification](https://mlsanity.com/paper/2502.11520/) (2025)
- [Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making](https://mlsanity.com/paper/2505.19933/) (2025)
- [Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models](https://mlsanity.com/paper/2506.09532/) (2025)
- [Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text](https://mlsanity.com/paper/2402.13415/) (2024)
- [Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment](https://mlsanity.com/paper/2502.11244/) (2025)
- [From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment](https://mlsanity.com/paper/2506.12446/) (2025)
- [Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision](https://mlsanity.com/paper/2505.19706/) (2025)
- [SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues](https://mlsanity.com/paper/2506.00668/) (2025)
- [Scalable Oversight for Superhuman AI via Recursive Self-Critiquing](https://mlsanity.com/paper/2502.04675/) (2025)

## Built on by (most cited first, 2 of 2)

- [Towards Robust Process Reward Modeling via Noise-aware Learning](https://mlsanity.com/paper/2601.12748/) (2026)
- [MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency Contexts](https://mlsanity.com/paper/2601.18790/) (2026)

## Abstract (arXiv)

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar outcome-based reward models, parameter tuning, or heuristic decoding strategies, lack the granularity and proactive nature needed to reliably detect and intervene during subtle yet crucial reasoning steps. Addressing this fundamental gap, we introduce AURA, an innovative, multi-layered framework centered around Process Reward Models (PRMs), providing comprehensive, step level evaluations across logical coherence and safety-awareness. Our framework seamlessly combines introspective self-critique, fine-grained PRM assessments, and adaptive safety-aware decoding to dynamically and proactively guide models toward safer reasoning trajectories. Empirical evidence clearly demonstrates that this approach significantly surpasses existing methods, significantly improving the logical integrity and affordance-sensitive safety of model outputs. This research represents a pivotal step toward safer, more responsible, and contextually aware AI, setting a new benchmark for alignment-sensitive applications.