1 code implementation • 10 Feb 2024 • Ankit Pal, Malaikannan Sankarasubbu
Additionally, we facilitated future research and development by releasing a Python module for medical LLM evaluation and establishing a dedicated leaderboard on Hugging Face for medical domain LLMs.
1 code implementation • 19 Oct 2023 • Ankit Pal
Our findings emphasize the need for and the potential for increasing the robustness of clinical domain models under distributional shifts.
1 code implementation • 28 Jul 2023 • Ankit Pal, Logesh Kumar Umapathi, Malaikannan Sankarasubbu
This research paper focuses on the challenges posed by hallucinations in large language models (LLMs), particularly in the context of the medical domain.
no code implementations • 15 Nov 2022 • Madhura Joshi, Ankit Pal, Malaikannan Sankarasubbu
Federated learning is the process of developing machine learning models over datasets distributed across data centers such as hospitals, clinical research labs, and mobile devices while preventing data leakage.
1 code implementation • 15 Nov 2022 • Ankit Pal
This paper introduces DeepParliament, a legal domain Benchmark Dataset that gathers bill documents and metadata and performs various bill status classification tasks.
1 code implementation • 27 Mar 2022 • Ankit Pal, Logesh Kumar Umapathi, Malaikannan Sankarasubbu
This paper introduces MedMCQA, a new large-scale, Multiple-Choice Question Answering (MCQA) dataset designed to address real-world medical entrance exam questions.
Ranked #7 on Multiple Choice Question Answering (MCQA) on MedMCQA
1 code implementation • 6 Oct 2020 • Ankit Pal, Malaikannan Sankarasubbu
COVID-19 (coronavirus disease 2019) pandemic caused by SARS-CoV-2 has led to a treacherous and devastating catastrophe for humanity.
2 code implementations • 22 Mar 2020 • Ankit Pal, Muru Selvakumar, Malaikannan Sankarasubbu
The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task.
2 code implementations • 12th International Conference on Agents and Artificial Intelligence ICAART 2020 • Ankit Pal, Muru Selvakumar and Malaikannan Sankarasubbu
The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task.
Ranked #1 on Multi-Label Text Classification on Slashdot