AI Paper Atlas

Research map / Large language models / Alignment and preferences

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

Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee, Rima Hazra, Somak Aditya, Animesh Mukherjee

AAAI 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-critique to PRM-guided selection (best-of-8) (ablation)AURA · SituationAfford safety ratesafety rate: 0.34 -> 0.52 (@2 vs w/o self-critique, Qwen2.5-7B)Improved
increase number of sampled trajectories from 2 to 8 (ablation)AURA · SituationAfford safety ratesafety rate: 0.52 -> 0.71 (Qwen2.5-7B)Improved
add AURA reward-guided decodinginstruction-tuned 7-9B LLMs · SituationAfford safety ratesafety rate: 0.28 -> 0.71 (Qwen2.5-7B)Improved
add self-critique only (no PRM selection) (ablation)base LLMs · SituationAfford safety ratesafety rate: 0.28 -> 0.34 (Qwen2.5-7B)Improved
add full AURA pipelineinstruction-tuned LLMs · CoSafe / STREAMASR: 0.15 -> 0.08 (CoSafe, Qwen2.5-7B)Improved
add self-critique on top of PRM (ablation)AURA · SituationAfford ASRASR: 0.33 -> 0.22 (Qwen2.5-7B)Improved
train AffordRanker as step-level PRM vs existing PRMsstep-level classification · SituationAfford step-levelF1: 0.68 -> 0.88 (balanced coherence vs PathFinder-PRM-7B)Improved
apply AURA at inferenceLlama-3.1-8B · MMLU / ARC-Challengeaccuracy: 65.6-66.2 -> 65.2-65.9 (MMLU)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy