A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks

CX Liang, P Tian, CH Yin, Y Yua, W An-Hou… - arXiv preprint arXiv …, 2024 - arxiv.org
This survey and application guide to multimodal large language models (MLLMs) explores
the rapidly developing field of MLLMs, examining their architectures, applications, and …

CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation

AB Hou, O Weller, G Qin, E Yang, D Lawrie… - arXiv preprint arXiv …, 2024 - arxiv.org
Legal professionals need to write analyses that rely on citations to relevant precedents, ie,
previous case decisions. Intelligent systems assisting legal professionals in writing such …

Belief in the Machine: Investigating Epistemological Blind Spots of Language Models

M Suzgun, T Gur, F Bianchi, DE Ho, T Icard… - arXiv preprint arXiv …, 2024 - arxiv.org
As language models (LMs) become integral to fields like healthcare, law, and journalism,
their ability to differentiate between fact, belief, and knowledge is essential for reliable …

Unboxing generative AI for the legal professions: functions, impacts and governance

F Contini - IJCA, 2024 - HeinOnline
Artificial intelligence has been promising to transform the legalfield and administration
ofjustice for more than thirty years.'The ambition to have roboticjudges capable of deciding …

It cannot be right if it was written by AI: on lawyers' preferences of documents perceived as authored by an LLM vs a human

J Harasta, T Novotná, J Savelka - Artificial Intelligence and Law, 2024 - Springer
Abstract Large Language Models (LLMs) enable a future in which certain types of legal
documents may be generated automatically. This has a great potential to streamline legal …

Gaps or hallucinations? scrutinizing machine-generated legal analysis for fine-grained text evaluations

A Hou, W Jurayj, N Holzenberger… - Proceedings of the …, 2024 - aclanthology.org
Abstract Large Language Models (LLMs) show promise as a writing aid for professionals
performing legal analyses. However, LLMs can often hallucinate in this setting, in ways …

Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations

AB Hou, W Jurayj, N Holzenberger… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) show promise as a writing aid for professionals performing
legal analyses. However, LLMs can often hallucinate in this setting, in ways difficult to …

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications

R Kalra, Z Wu, A Gulley, A Hilliard, X Guan… - arXiv preprint arXiv …, 2024 - arxiv.org
While Large Language Models (LLMs) excel in text generation and question-answering,
their effectiveness in AI legal and policy is limited by outdated knowledge, hallucinations …

Exploring the practicality of generative retrieval on dynamic corpora

C Kim, S Yoon, H Lee, J Jang, S Yang… - arXiv preprint arXiv …, 2023 - arxiv.org
Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed
set of documents (static corpora). However, in realistic scenarios, this is rarely the case and …

Enhancing Trust in Large Language Models with Uncertainty-Aware Fine-Tuning

R Krishnan, P Khanna, O Tickoo - arXiv preprint arXiv:2412.02904, 2024 - arxiv.org
Large language models (LLMs) have revolutionized the field of natural language processing
with their impressive reasoning and question-answering capabilities. However, these …