Feb. 6, 2024, 5:54 a.m. | Aman Tiwari Prathamesh Kalamkar Atreyo Banerjee Saurabh Karn Varun Hemachandran Smita Gupta

cs.CL updates on arXiv.org arxiv.org

Using proprietary Large Language Models on legal tasks poses challenges due to data privacy issues, domain data heterogeneity, domain knowledge sophistication, and domain objectives uniqueness. We created Aalalp, a fine-tuned Mistral 7B model on instructions data related to specific Indian legal tasks. The performance of Aalap is better than gpt-3.5-turbo in 31\% of our test data and obtains an equivalent score in 34\% of the test data as evaluated by GPT4. Training Aalap mainly focuses on teaching legal reasoning rather …

ai assistant assistant challenges cs.ai cs.cl cs.cy data data privacy domain domain knowledge functions gpt gpt-3 gpt-3.5 gpt-3.5-turbo india indian knowledge language language models large language large language models legal mistral mistral 7b performance privacy proprietary tasks turbo

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne