Mitigating Hallucinations in Healthcare LLMs with Granular Fact-Checking and Domain-Specific Adaptation

• URL: http://arxiv.org/abs/2512.16189v2
• Date: Fri, 19 Dec 2025 06:34:23 GMT
• Title: Mitigating Hallucinations in Healthcare LLMs with Granular Fact-Checking and Domain-Specific Adaptation
• Authors: Musarrat Zeba, Abdullah Al Mamun, Kishoar Jahan Tithee, Debopom Sutradhar, Mohaimenul Azam Khan Raiaan, Saddam Mukta, Reem E. Mohamed, Md Rafiqul Islam, Yakub Sebastian, Mukhtar Hussain, Sami Azam,
• Abstract summary: We propose a fact-checking module that operates independently of any LLM.<n>Our model is fine-tuned using Low-Rank Adaptation (LoRa) on the MIMIC III dataset.<n>The fact-checking module achieves a precision of 0.8904, a recall of 0.8234, and an F1-score of 0.8556.
• Score: 2.455449872438139
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In healthcare, it is essential for any LLM-generated output to be reliable and accurate, particularly in cases involving decision-making and patient safety. However, the outputs are often unreliable in such critical areas due to the risk of hallucinated outputs from the LLMs. To address this issue, we propose a fact-checking module that operates independently of any LLM, along with a domain-specific summarization model designed to minimize hallucination rates. Our model is fine-tuned using Low-Rank Adaptation (LoRa) on the MIMIC III dataset and is paired with the fact-checking module, which uses numerical tests for correctness and logical checks at a granular level through discrete logic in natural language processing (NLP) to validate facts against electronic health records (EHRs). We trained the LLM model on the full MIMIC-III dataset. For evaluation of the fact-checking module, we sampled 104 summaries, extracted them into 3,786 propositions, and used these as facts. The fact-checking module achieves a precision of 0.8904, a recall of 0.8234, and an F1-score of 0.8556. Additionally, the LLM summary model achieves a ROUGE-1 score of 0.5797 and a BERTScore of 0.9120 for summary quality.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs [16.173245551933178]
  Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text.<n>We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing complex evaluation pipelines.
  arXiv  Detail & Related papers  (2025-09-26T17:03:24Z)
• Evaluating Large Language Models for Zero-Shot Disease Labeling in CT Radiology Reports Across Organ Systems [1.1373722549440357]
  We compare a rule-based algorithm (RBA), RadBERT, and three lightweight open-weight LLMs for multi-disease labeling of chest, abdomen, and pelvis CT reports.<n>Performance was evaluated using Cohen's Kappa and micro/macro-averaged F1 scores.
  arXiv  Detail & Related papers  (2025-06-03T18:00:08Z)
• Structuring Radiology Reports: Challenging LLMs with Lightweight Models [5.01440254761063]
  Large language models (LLMs) have shown strong capabilities in reformatting clinical text, their high computational requirements, lack of transparency, and data privacy concerns hinder practical deployment.<n>We explore lightweight encoder-decoder models (300M parameters)-specifically T5 and BERT2BERT-for structuring radiology reports from the MIMIC-CXR and CheXpert Plus datasets.<n>Our best-performing lightweight model outperforms all LLMs adapted using prompt-based techniques on a human-annotated test set.
  arXiv  Detail & Related papers  (2025-05-30T20:12:51Z)
• ELM: Ensemble of Language Models for Predicting Tumor Group from Pathology Reports [2.0447192404937353]
  Population-based cancer registries (PBCRs) face a significant bottleneck in manually extracting data from unstructured pathology reports.<n>We introduce ELM, a novel ensemble-based approach leveraging both small language models (SLMs) and large language models (LLMs)<n>ELM achieves an average precision and recall of 0.94, outperforming single-model and ensemble-without-LLM approaches.
  arXiv  Detail & Related papers  (2025-03-24T19:21:53Z)
• Preference Leakage: A Contamination Problem in LLM-as-a-judge [69.96778498636071]
  Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods.<n>In this work, we expose preference leakage, a contamination problem in LLM-as-a-judge caused by the relatedness between the synthetic data generators and LLM-based evaluators.
  arXiv  Detail & Related papers  (2025-02-03T17:13:03Z)
• Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology [3.0048953993445586]
  This study aims to use a large language model (LLM) to automate the generation of summaries from the CT simulation orders.<n>A locally hosted Llama 3.1 405B model was used to extract keywords from the CT simulation orders and generate summaries.<n>The accuracy of the LLM-generated summaries was evaluated by therapists using the verified ground truth as a reference.
  arXiv  Detail & Related papers  (2025-01-27T18:47:58Z)
• Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output [49.893971654861424]
  We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG) We compute a factuality score that can be thresholded to yield a binary decision. Our experiments show high area under the ROC curve (AUC) across a wide range of relevant open source datasets.
  arXiv  Detail & Related papers  (2024-11-01T20:44:59Z)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.