# MedHal-Loc: Are "Explainable-by-Architecture" Medical Hallucination Detectors Faithful Localizers? A Localization Benchmark

arXiv: https://arxiv.org/abs/2606.21517 · HTML: https://mlsanity.com/paper/2606.21517/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [Med-HALT: Medical Domain Hallucination Test for Large Language Models](https://mlsanity.com/paper/2307.15343/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework](https://mlsanity.com/paper/2407.10793/) (2024)
- [Hallucination Detection in Large Language Models with Metamorphic Relations](https://mlsanity.com/paper/2502.15844/) (2025)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling](https://mlsanity.com/paper/2409.11283/) (2024)

## Abstract (arXiv)

Detecting hallucinations in clinical text is increasingly framed as an explainability problem: systems should not merely flag an unreliable response but point to the offending span. Architectures built around knowledge-graph (KG) triple decomposition are marketed for exactly this auditability, yet their localization ability is typically assumed rather than measured. We introduce MedHal-Loc, a benchmark and metric for localization faithfulness -- whether a detector's top-ranked error unit actually overlaps the erroneous span. The controlled subset comprises 300 PubMedQA-derived statements with single, span-level errors injected across four localizable types (entity substitution, relation error, mechanism misattribution, invention), yielding gold spans by construction; a complementary natural subset documents that real hallucinations are dominated by diffuse conclusion-flips that resist span localization (a human expert accepted 1/18 candidate spans). Evaluating four fine-grained paradigms, we find that NLI-per-clause, consistency-per-sentence, and the dedicated span detector FAVA all localize well above chance, whereas an elaborate KG-triple pipeline localizes no better than chance (+3.3pp, n.s.), bottlenecked by ~59% entity-extraction coverage -- despite competitive detection F1 (0.609). Detection competence does not imply faithful localization; architectural explainability must be validated, not presumed.