Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models
On the map: LLM reasoning → Test-time compute and efficient thinking
Abstract (arXiv)
Large language models (LLMs) often generate reasoning traces that appear coherent but rest on unsupported assumptions, leading to hallucinated conclusions. Prior work mainly addresses factual hallucinations or relies on post-hoc verification, leaving reasoning-induced hallucinations largely unaddressed. We propose Audit-of-Understanding (AoU), a framework that constrains inference to validated premises through three phases: (1) decomposing a query into candidate assumptions, (2) auditing their support, and (3) conditioning inference only on the validated subset. Formally, AoU is posterior-constrained inference, connecting to selective prediction and rejection learning. Our contributions are threefold: (i) theoretical guarantees under perfect validation, (ii) excess-risk bounds under imperfect audits, and (iii) tractability analysis. Empirically, AoU improves both accuracy and faithfulness on GSM8K, MultiArith, and SVAMP, achieving up to +30% gains on GSM8K, +45% on MultiArith, and consistent +20--28% improvements on SVAMP over Chain-of-Thought, Self-Consistency, and CoT-Decoding. Code is available at https://anonymous.4open.science/r/audit-of-understanding-E28B.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 2 of its 25 references that are in the map. First posted on arXiv 11 Oct 2025.
Builds on
2 of 25 references.
Closest ancestors · 1
Same direction, newest first
- 2024Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic29 Aug
Other references · 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026RAudit: A Blind Auditing Protocol for Large Language Model Reasoning
- 2025BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
- 2025Examining False Positives under Inference Scaling for Mathematical Reasoning
- 2025Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
- 2025Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations
- 2025Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
- 2026REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
- 2025Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs