mlsanityData to 7 Oct 2026

HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making

arXiv 2409.10011 ↗First posted 16 Sep 2024cs.CL cs.AIcited by 3

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health and medicine, these hallucinations can pose serious risks. This paper introduces HALO, a novel framework designed to enhance the accuracy and reliability of medical question-answering (QA) systems by focusing on the detection and mitigation of hallucinations. Our approach generates multiple variations of a given query using LLMs and retrieves relevant information from external open knowledge bases to enrich the context. We utilize maximum marginal relevance scoring to prioritize the retrieved context, which is then provided to LLMs for answer generation, thereby reducing the risk of hallucinations. The integration of LangChain further streamlines this process, resulting in a notable and robust increase in the accuracy of both open-source and commercial LLMs, such as Llama-3.1 (from 44% to 65%) and ChatGPT (from 56% to 70%). This framework underscores the critical importance of addressing hallucinations in medical QA systems, ultimately improving clinical decision-making and patient care. The open-source HALO is available at: https://github.com/ResponsibleAILab/HALO.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 41 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

27 of 41 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  4. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  6. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  7. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  8. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  9. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  10. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  11. 2023How Language Model Hallucinations Can Snowballcited by 310
  12. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
15 more
  1. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  2. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 137
  3. 2023In-context Pretraining: Language Modeling Beyond Document Boundariescited by 76
  4. 2023Large Language Models can Learn Rulescited by 66
  5. 2022Legal Prompting: Teaching a Language Model to Think Like a Lawyercited by 60
  6. 2022Entity Cloze By Date: What LMs Know About Unseen Entitiescited by 55
  7. 2023Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucinationcited by 41
  8. 2023PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domaincited by 40
  9. 2024Retrieval Augmented Generation for Domain-specific Question Answeringcited by 22
  10. 2024OLAPH: Improving Factuality in Biomedical Long-form Question Answeringcited by 20
  11. 2023Augmenting LLMs with Knowledge: A survey on hallucination preventioncited by 16
  12. 2023From Beginner to Expert: Modeling Medical Knowledge into General LLMscited by 14
  13. 2023Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialoguescited by 5
  14. 2023Hallucination Reduction in Long Input Text Summarizationcited by 5
  15. 2024Large Language Models for Multi-Choice Question Classification of Medical Subjectscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 6
  2. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  3. 2026Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loopscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models
  2. 2026Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
  3. 2024Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots
  4. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answering
  5. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  6. 2024MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
  7. 2024HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild
  8. 2025Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs