Hi! My name is Abhika Mishra 👋
I’m a passionate computer science student deeply committed to advancing the field of artificial intelligence (AI) with a focus on Natural Language Processing (NLP). As an Undergraduate Researcher at the University of Washington, I explore innovative approaches to enhance language models’ trustworthiness and quality, particularly in detecting hallucinations within LM outputs. I am excited to contribute my skills and insights to the ever-evolving landscape of ethical and transformative technology.
- Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang, Graham Neubig, Yulia Tsvetkov, and Hannaneh Hajishirzi
Fine-grained Hallucination Detection and Editing for Language Models [Paper], [Website], [Code], [Model], [Demo]
Name | Description | Tooling |
---|---|---|
FAVA | Evaluation, retrieval, and training code for research paper: Fine-grained Hallucination Detection and Editing for Language Models. | |
CropUp | DUBHACKS WINNER 2022. Web application to determine best crops to grow in your area based on plant hardiness zone predicted by machine learning model trained on current climate's data. | |
Equify | Applied Natural Language Processing model using Stanford's CoreNLP library to identify names and then diversify them | |
Cloude | Realtime collaborative coding IDE. Submitted to Dubhacks 2021. | |
NLP Research Summaries | My summaries of some recent papers in the ML and NLP domain |
Award | Issuer |
---|---|
Winner of Dubhacks 2022 | Dubhacks at UW |
Winner of Decoded Hacks 2020 | Decoded |