{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T05:23:14Z","timestamp":1772515394622,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"Microsoft Accelerate Foundation Models Research Grant"},{"name":"National Institute on Aging (NIA)","award":["R21AG087192"],"award-info":[{"award-number":["R21AG087192"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,24]]},"DOI":"10.1145\/3721201.3721385","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:35:21Z","timestamp":1762954521000},"page":"187-198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0565-6719","authenticated-orcid":false,"given":"Sumera","family":"Anjum","sequence":"first","affiliation":[{"name":"University of North Texas, Denton, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0145-9814","authenticated-orcid":false,"given":"Hanzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2346-8151","authenticated-orcid":false,"given":"Wenjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Knoxville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3826-8243","authenticated-orcid":false,"given":"Eun Jin","family":"Paek","sequence":"additional","affiliation":[{"name":"University of Tennessee Health Science Center, Knoxville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1207-5379","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6577-227X","authenticated-orcid":false,"given":"Yunhe","family":"Feng","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00667"},{"key":"e_1_3_2_1_2_1","unstructured":"Anakin AI. 2023. What is GPT-3.5 Turbo Instruct? https:\/\/anakin.ai\/blog\/what-is-gpt-3-5-turbo-instruct\/"},{"key":"e_1_3_2_1_3_1","volume-title":"Augmenting LLMs with Knowledge: A survey on hallucination prevention. arXiv preprint arXiv:2309.16459","author":"Andriopoulos Konstantinos","year":"2023","unstructured":"Konstantinos Andriopoulos and Johan Pouwelse. 2023. Augmenting LLMs with Knowledge: A survey on hallucination prevention. arXiv preprint arXiv:2309.16459 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Biomedlm: A 2.7 b parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421","author":"Bolton Elliot","year":"2024","unstructured":"Elliot Bolton, Abhinav Venigalla, Michihiro Yasunaga, David Hall, Betty Xiong, Tony Lee, Roxana Daneshjou, Jonathan Frankle, Percy Liang, Michael Carbin, et al. 2024. Biomedlm: A 2.7 b parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues. arXiv preprint arXiv:2309.11838","author":"Braunschweiler Norbert","year":"2023","unstructured":"Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, and Svetlana Stoyanchev. 2023. Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues. arXiv preprint arXiv:2309.11838 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Discovering latent knowledge in language models without supervision. arXiv preprint arXiv:2212.03827","author":"Burns Collin","year":"2022","unstructured":"Collin Burns, Haotian Ye, Dan Klein, and Jacob Steinhardt. 2022. Discovering latent knowledge in language models without supervision. arXiv preprint arXiv:2212.03827 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"e_1_3_2_1_8_1","unstructured":"Harrison Chase. 2023. Multi Query Retriever. Online. Available at https:\/\/python.langchain.com\/v0.1\/docs\/modules\/data_connection\/retrievers\/MultiQueryRetriever\/."},{"key":"e_1_3_2_1_9_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2023. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. arXiv preprint arXiv:2311.05232 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering. arXiv preprint arXiv:2405.12701","author":"Jeong Minbyul","year":"2024","unstructured":"Minbyul Jeong, Hyeon Hwang, Chanwoong Yoon, Taewhoo Lee, and Jaewoo Kang. 2024. OLAPH: Improving Factuality in Biomedical Long-form Question Answering. arXiv preprint arXiv:2405.12701 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Andrea Madotto, and Pascale Fung.","author":"Ji Ziwei","year":"2023","unstructured":"Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM computing surveys 55, 12 (2023), 1\u201338."},{"key":"e_1_3_2_1_14_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination. arXiv preprint arXiv:2311.15548","author":"Kang Haoqiang","year":"2023","unstructured":"Haoqiang Kang and Xiao-Yang Liu. 2023. Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination. arXiv preprint arXiv:2311.15548 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.234"},{"key":"e_1_3_2_1_17_1","volume-title":"Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499","author":"Lee Katherine","year":"2021","unstructured":"Katherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang, Douglas Eck, Chris Callison-Burch, and Nicholas Carlini. 2021. Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Expert: Modeling Medical Knowledge into General LLMs. arXiv preprint arXiv:2312.01040","author":"Li Qiang","year":"2023","unstructured":"Qiang Li, Xiaoyan Yang, Haowen Wang, Qin Wang, Lei Liu, Junjie Wang, Yang Zhang, Mingyuan Chu, Sen Hu, Yicheng Chen, et al. 2023. From Beginner to Expert: Modeling Medical Knowledge into General LLMs. arXiv preprint arXiv:2312.01040 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge. Cureus 15, 6","author":"Li Yunxiang","year":"2023","unstructured":"Yunxiang Li, Zihan Li, Kai Zhang, Ruilong Dan, Steve Jiang, and You Zhang. 2023. Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge. Cureus 15, 6 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li\u00e9vin Valentin","year":"2023","unstructured":"Valentin Li\u00e9vin, Andreas Geert Motzfeldt, Ida Riis Jensen, and Ole Winther. 2023. Variational open-domain question answering. In International Conference on Machine Learning. PMLR, 20950\u201320977."},{"key":"e_1_3_2_1_21_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_1_22_1","volume-title":"Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi.","author":"Min Sewon","year":"2023","unstructured":"Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. arXiv preprint arXiv:2305.14251 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Eunsol Choi, and Greg Durrett.","author":"Onoe Yasumasa","year":"2022","unstructured":"Yasumasa Onoe, Michael JQ Zhang, Eunsol Choi, and Greg Durrett. 2022. Entity cloze by date: What LMs know about unseen entities. arXiv preprint arXiv:2205.02832 (2022)."},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2023. GPT-3.5 Turbo. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5-turbo"},{"key":"e_1_3_2_1_25_1","volume-title":"Conference on health, inference, and learning. PMLR, 248\u2013260","author":"Pal Ankit","year":"2022","unstructured":"Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In Conference on health, inference, and learning. PMLR, 248\u2013260."},{"key":"e_1_3_2_1_26_1","volume-title":"Large Language Models for Multi-Choice Question Classification of Medical Subjects. arXiv preprint arXiv:2403.14582","author":"Ponce-L\u00f3pez V\u00edctor","year":"2024","unstructured":"V\u00edctor Ponce-L\u00f3pez. 2024. Large Language Models for Multi-Choice Question Classification of Medical Subjects. arXiv preprint arXiv:2403.14582 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732","author":"Ranzato Marc'Aurelio","year":"2015","unstructured":"Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)."},{"key":"e_1_3_2_1_28_1","unstructured":"Wamiq Raza. 2024. Leveraging Meta's LLaMA 3.1 for Efficient Question-Answering on Google Colab. https:\/\/medium.com\/@WamiqRaza\/leveraging-metas-llama-3-1-for-efficient-question-answering-on-google-colab-e4f04d84e56e"},{"key":"e_1_3_2_1_29_1","volume-title":"Evaluation of the performance of GPT-3.5 and GPT-4 on the Medical Final Examination. medRxiv","author":"Roso\u0142 Maciej","year":"2023","unstructured":"Maciej Roso\u0142, Jakub S G\u0105sior, Jonasz \u0141aba, Kacper Korzeniewski, and Marcel M\u0142y\u0144czak. 2023. Evaluation of the performance of GPT-3.5 and GPT-4 on the Medical Final Examination. medRxiv (2023), 2023\u201306."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Computational Science. Springer, 222\u2013230","author":"Shaik Kareem","year":"2024","unstructured":"Kareem Shaik, Dali Wang, Weijian Zheng, Qinglei Cao, Heng Fan, Peter Schwartz, and Yunhe Feng. 2024. S3LLM: Large-S cale S cientific S oftware Understanding with LLMs Using Source, Metadata, and Document. In International Conference on Computational Science. Springer, 222\u2013230."},{"key":"e_1_3_2_1_31_1","volume-title":"Franck Dernoncourt, Dewang Sultania, Karishma Bagga, Mengjiao Zhang, Trung Bui, and Varun Kotte.","author":"Sharma Sanat","year":"2024","unstructured":"Sanat Sharma, David Seunghyun Yoon, Franck Dernoncourt, Dewang Sultania, Karishma Bagga, Mengjiao Zhang, Trung Bui, and Varun Kotte. 2024. Retrieval Augmented Generation for Domain-specific Question Answering. arXiv preprint arXiv:2404.14760 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"In-Context Pretraining: Language Modeling Beyond Document Boundaries. arXiv preprint arXiv:2310.10638","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Maria Lomeli, Chunting Zhou, Margaret Li, Victoria Lin, Noah A Smith, Luke Zettlemoyer, Scott Yih, and Mike Lewis. 2023. In-Context Pretraining: Language Modeling Beyond Document Boundaries. arXiv preprint arXiv:2310.10638 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks. ArXiv abs\/2402.08115","author":"Stechly Kaya","year":"2024","unstructured":"Kaya Stechly, Karthik Valmeekam, and Subbarao Kambhampati. 2024. On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks. ArXiv abs\/2402.08115 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267637077"},{"key":"e_1_3_2_1_34_1","volume-title":"One embedder, any task: Instruction-finetuned text embeddings. arXiv preprint arXiv:2212.09741","author":"Su Hongjin","year":"2022","unstructured":"Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A Smith, Luke Zettlemoyer, and Tao Yu. 2022. One embedder, any task: Instruction-finetuned text embeddings. arXiv preprint arXiv:2212.09741 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355","author":"Thorne James","year":"2018","unstructured":"James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355 (2018)."},{"key":"e_1_3_2_1_36_1","volume-title":"Medhalt: Medical domain hallucination test for large language models. arXiv preprint arXiv:2307.15343","author":"Umapathi Logesh Kumar","year":"2023","unstructured":"Logesh Kumar Umapathi, Ankit Pal, and Malaikannan Sankarasubbu. 2023. Medhalt: Medical domain hallucination test for large language models. arXiv preprint arXiv:2307.15343 (2023)."},{"key":"e_1_3_2_1_37_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_38_1","volume-title":"Legal prompting: Teaching a language model to think like a lawyer. arXiv preprint arXiv:2212.01326","author":"Yu Fangyi","year":"2022","unstructured":"Fangyi Yu, Lee Quartey, and Frank Schilder. 2022. Legal prompting: Teaching a language model to think like a lawyer. arXiv preprint arXiv:2212.01326 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Evaluation of Retrieval-Augmented Generation: A Survey. arXiv preprint arXiv:2405.07437","author":"Yu Hao","year":"2024","unstructured":"Hao Yu, Aoran Gan, Kai Zhang, Shiwei Tong, Qi Liu, and Zhaofeng Liu. 2024. Evaluation of Retrieval-Augmented Generation: A Survey. arXiv preprint arXiv:2405.07437 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"How language model hallucinations can snowball. arXiv preprint arXiv:2305.13534","author":"Zhang Muru","year":"2023","unstructured":"Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A Smith. 2023. How language model hallucinations can snowball. arXiv preprint arXiv:2305.13534 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain. arXiv e-prints. arXiv preprint arXiv:2310.14151","author":"Zhu W","year":"2023","unstructured":"W Zhu, X Wang, H Zheng, M Chen, and B Tang. 2023. PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain. arXiv e-prints. arXiv preprint arXiv:2310.14151 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Large language models can learn rules. arXiv preprint arXiv:2310.07064","author":"Zhu Zhaocheng","year":"2023","unstructured":"Zhaocheng Zhu, Yuan Xue, Xinyun Chen, Denny Zhou, Jian Tang, Dale Schuurmans, and Hanjun Dai. 2023. Large language models can learn rules. arXiv preprint arXiv:2310.07064 (2023)."}],"event":{"name":"CHASE '25: ACM\/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","location":"Yeshiva University Museum New York NY USA","acronym":"CHASE '25","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","IEEE Computer Society"]},"container-title":["Proceedings of the ACM\/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721201.3721385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:36:17Z","timestamp":1762954577000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721201.3721385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":42,"alternative-id":["10.1145\/3721201.3721385","10.1145\/3721201"],"URL":"https:\/\/doi.org\/10.1145\/3721201.3721385","relation":{},"subject":[],"published":{"date-parts":[[2025,6,24]]},"assertion":[{"value":"2025-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}