# When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL~2~DL

arXiv: https://arxiv.org/abs/2604.23398 · HTML: https://mlsanity.com/paper/2604.23398/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Graph Neural Network-Driven Hierarchical Mining for Complex Imbalanced Data](https://mlsanity.com/paper/2502.03803/) (2025)
- [Structured Memory Mechanisms for Stable Context Representation in Large Language Models](https://mlsanity.com/paper/2505.22921/) (2025)
- [Benchmarking Large Language Models for Image Classification of Marine Mammals](https://mlsanity.com/paper/2410.19848/) (2024)
- [Coverage-Aware Web Crawling for Domain-Specific Supplier Discovery via a Web--Knowledge--Web Pipeline](https://mlsanity.com/paper/2602.24262/) (2026)
- [Large Language Model for OWL Proofs](https://mlsanity.com/paper/2601.12444/) (2026)
- [Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2602.19591/) (2026)

## Built on by (most cited first, 1 of 1)

- [Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite](https://mlsanity.com/paper/2606.11257/) (2026)

## Abstract (arXiv)

We report a reproducible error pattern in GPT-5.4 on OWL~2~DL compliance queries: the model frequently answers ``unknown'' when the reasoner-entailed answer is ``no'' under FunctionalProperty closure or class disjointness. Using 180 reasoner-audited queries from a procedural expansion of the observed pattern plus 18 hand-authored held-out queries in two unrelated domains (insurance and clinical), we compare four interaction modes under matched query budget: single-shot, three rounds of generic ``you-are-wrong'' retry, three rounds of reasoner-verdict repair with an open-world-assumption (OWA) hint, and the same repair without the hint. Direct faithfulness is 43.9,% (Wilson 95,% CI [36.8,51.2]); generic retry reaches 81.7,% ([75.4,86.6]); the verdict-with-hint variant is worse at 67.2,% ([60.1,73.7]); the verdict-only variant reaches 97.8,% ([94.4,99.1]). All pairwise comparisons remain significant under McNemar's exact test with Bonferroni correction (α = 0.01; all p < 10-5). The same fingerprint accounts for 4/4 errors on the held-out queries. Our interpretation is bounded: prompt framing can matter more than corrective content, and reasoner-guided wrappers should be ablated explicitly.