PARAMANU-AYN: An Efficient Novel Generative and Instruction-tuned Language Model for Indian Legal Case Documents | allainews.com

March 21, 2024, 4:42 a.m. | Mitodru Niyogi, Arnab Bhattacharya

cs.LG updates on arXiv.org arxiv.org

arXiv:2403.13681v1 Announce Type: cross
Abstract: In this paper, we present PARAMANU-AYN, a language model based exclusively on case documents of the Supreme Court of India, the Constitution of India, and the Indian Penal Code. The novel Auto Regressive (AR) decoder based model is pretrained from scratch at a context size of 8192. We evaluated our pretrained legal model on perplexity metrics. We also instruction-tuned our pretrained model on a set of 10,763 instructions covering various legal tasks such as legal …

arxiv case cs.ai cs.cl cs.lg documents generative indian instruction-tuned language language model legal novel type

More from arxiv.org / cs.LG updates on arXiv.org

Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks 10 hours ago | arxiv.org

abstract applications arxiv attacks +24

Secure Transformer Inference Protocol 10 hours ago | arxiv.org

abstract adoption arxiv chatgpt +18

Speech Understanding on Tiny Devices with A Learning Cache 10 hours ago | arxiv.org

abstract arxiv cache cloud +23

Particle density and critical point for studying site percolation by finite size scaling 10 hours ago | arxiv.org

abstract arxiv cond-mat.stat-mech cs.lg +14

Online Long-run Constrained Optimization 10 hours ago | arxiv.org

abstract algorithm arxiv constraints +12

Deep-learning-based decomposition of overlapping-sparse images: application at the vertex of neutrino interactions 10 hours ago | arxiv.org

abstract algorithms analysis application +22

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective 10 hours ago | arxiv.org

arxiv cs.ai cs.cl cs.lg +9

Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions 10 hours ago | arxiv.org

alignment analysis arxiv cs.cl +8

Solving Elliptic Optimal Control Problems via Neural Networks and Optimality System 10 hours ago | arxiv.org

abstract arxiv box control +13

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

View on ai-jobs.net

Lead Developer (AI)

@ Cere Network | San Francisco, US

View on ai-jobs.net

Research Engineer

@ Allora Labs | Remote

View on ai-jobs.net

Ecosystem Manager

@ Allora Labs | Remote

View on ai-jobs.net

Founding AI Engineer, Agents

@ Occam AI | New York

View on ai-jobs.net

AI Engineer Intern, Agents

@ Occam AI | US

View on ai-jobs.net