Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Agrawal, Atharva Mangeshkumar, Shinde, Rutika Pandurang, Bhukya, Vasanth Kumar, Chakraborty, Ashmita, Shah, Sagar Bharat, Shukla, Tanmay, Relangi, Sree Pradeep Kumar, Mutyam, Nilesh
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910813894213632
author Agrawal, Atharva Mangeshkumar
Shinde, Rutika Pandurang
Bhukya, Vasanth Kumar
Chakraborty, Ashmita
Shah, Sagar Bharat
Shukla, Tanmay
Relangi, Sree Pradeep Kumar
Mutyam, Nilesh
author_facet Agrawal, Atharva Mangeshkumar
Shinde, Rutika Pandurang
Bhukya, Vasanth Kumar
Chakraborty, Ashmita
Shah, Sagar Bharat
Shukla, Tanmay
Relangi, Sree Pradeep Kumar
Mutyam, Nilesh
contents Large language models (LLMs) have shown impressive capabilities in natural language processing tasks, including dialogue generation. This research aims to conduct a novel comparative analysis of two prominent techniques, fine-tuning with LoRA (Low-Rank Adaptation) and the Retrieval-Augmented Generation (RAG) framework, in the context of doctor-patient chat conversations with multiple datasets of mixed medical domains. The analysis involves three state-of-the-art models: Llama-2, GPT, and the LSTM model. Employing real-world doctor-patient dialogues, we comprehensively evaluate the performance of models, assessing key metrics such as language quality (perplexity, BLEU score), factual accuracy (fact-checking against medical knowledge bases), adherence to medical guidelines, and overall human judgments (coherence, empathy, safety). The findings provide insights into the strengths and limitations of each approach, shedding light on their suitability for healthcare applications. Furthermore, the research investigates the robustness of the models in handling diverse patient queries, ranging from general health inquiries to specific medical conditions. The impact of domain-specific knowledge integration is also explored, highlighting the potential for enhancing LLM performance through targeted data augmentation and retrieval strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02249
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation
Agrawal, Atharva Mangeshkumar
Shinde, Rutika Pandurang
Bhukya, Vasanth Kumar
Chakraborty, Ashmita
Shah, Sagar Bharat
Shukla, Tanmay
Relangi, Sree Pradeep Kumar
Mutyam, Nilesh
Computation and Language
Artificial Intelligence
Large language models (LLMs) have shown impressive capabilities in natural language processing tasks, including dialogue generation. This research aims to conduct a novel comparative analysis of two prominent techniques, fine-tuning with LoRA (Low-Rank Adaptation) and the Retrieval-Augmented Generation (RAG) framework, in the context of doctor-patient chat conversations with multiple datasets of mixed medical domains. The analysis involves three state-of-the-art models: Llama-2, GPT, and the LSTM model. Employing real-world doctor-patient dialogues, we comprehensively evaluate the performance of models, assessing key metrics such as language quality (perplexity, BLEU score), factual accuracy (fact-checking against medical knowledge bases), adherence to medical guidelines, and overall human judgments (coherence, empathy, safety). The findings provide insights into the strengths and limitations of each approach, shedding light on their suitability for healthcare applications. Furthermore, the research investigates the robustness of the models in handling diverse patient queries, ranging from general health inquiries to specific medical conditions. The impact of domain-specific knowledge integration is also explored, highlighting the potential for enhancing LLM performance through targeted data augmentation and retrieval strategies.
title Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.02249