Applicability of large language models and generative models for legal case judgement summarization

A Deroy, K Ghosh, S Ghosh - Artificial Intelligence and Law, 2024 - Springer
Automatic summarization of legal case judgements, which are known to be long and
complex, has traditionally been tried via extractive summarization models. In recent years …

A comprehensive survey of hallucination in large language, image, video and audio foundation models

P Sahoo, P Meharia, A Ghosh, S Saha… - Findings of the …, 2024 - aclanthology.org
The rapid advancement of foundation models (FMs) across language, image, audio, and
video domains has shown remarkable capabilities in diverse tasks. However, the …

Transformer models in healthcare: A survey and thematic analysis of potentials, shortcomings and risks

K Denecke, R May, O Rivera-Romero - Journal of Medical Systems, 2024 - Springer
Abstract Large Language Models (LLMs) such as General Pretrained Transformer (GPT)
and Bidirectional Encoder Representations from Transformers (BERT), which use …

How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior

K Wu, E Wu, J Zou - arxiv e-prints, 2024 - ui.adsabs.harvard.edu
Retrieval augmented generation (RAG) is often used to fix hallucinations and provide up-to-
date knowledge for large language models (LLMs). However, in cases when the LLM alone …

Clasheval: Quantifying the tug-of-war between an llm's internal prior and external evidence

K Wu, E Wu, J Zou - The Thirty-eight Conference on Neural …, 2024 - openreview.net
Retrieval augmented generation (RAG) is frequently used to mitigate hallucinations and
provide up-to-date knowledge for large language models (LLMs). However, given that …

Jmlr: Joint medical llm and retrieval training for enhancing reasoning and professional question answering capability

J Wang, Z Yang, Z Yao, H Yu - arxiv preprint arxiv:2402.17887, 2024 - arxiv.org
With the explosive growth of medical data and the rapid development of artificial intelligence
technology, precision medicine has emerged as a key to enhancing the quality and …

Large Language Models lack essential metacognition for reliable medical reasoning

M Griot, C Hemptinne, J Vanderdonckt… - Nature …, 2025 - nature.com
Abstract Large Language Models have demonstrated expert-level accuracy on medical
board examinations, suggesting potential for clinical decision support systems. However …

Fact-aware multimodal retrieval augmentation for accurate medical radiology report generation

L Sun, J Zhao, M Han, C **ong - arxiv preprint arxiv:2407.15268, 2024 - arxiv.org
Multimodal foundation models hold significant potential for automating radiology report
generation, thereby assisting clinicians in diagnosing cardiac diseases. However, generated …

Damro: Dive into the attention mechanism of lvlm to reduce object hallucination

X Gong, T Ming, X Wang, Z Wei - arxiv preprint arxiv:2410.04514, 2024 - arxiv.org
Despite the great success of Large Vision-Language Models (LVLMs), they inevitably suffer
from hallucination. As we know, both the visual encoder and the Large Language Model …

Biomedical Large Languages Models Seem not to be Superior to Generalist Models on Unseen Medical Data

FJ Dorfner, A Dada, F Busch, MR Makowski… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) have shown potential in biomedical applications, leading to
efforts to fine-tune them on domain-specific data. However, the effectiveness of this …