I am always interested in talking about industry research scientist and engineering positions in model evaluation, metric design, model explanation, and interpretation, and, work at the intersection of LLMs and productivity intermixed with design. If you have any in mind, please reach out to me.
I am also interested in collaborations around the area of LLM evaluation, real-world impact of LLMs and their failure analysis. If you have an interesting project, and would like to collaborate or talk, please email me.
Homepage, Email, Resume, Research Notes, and, Publications
Mimansa Jaiswal
NLP Researcher (Eval & XAI)
Hi, I'm Mimansa, a research scientist at Norm AI. I obtained my doctorate in Computer Science at the University of Michigan. My research
focuses on developing cost-effective data collection, manipulation and evaluation methods that are
interpretable and human aligned.
I've also interned at Allen AI NLP, Facebook AI Research
(FAIR) NLP, and Facebook Research Conversational AI, where I conducted research on similar topics.
Hi, I’m Mimansa
I’m Mimansa, a research scientist an Norm AI, working at the intersection of smart retrieval and evaluation for LLMs+Law. I’ve also interned at Allen AI NLP, Facebook AI Research(FAIR) NLP, and Facebook Research Conversational AI, where I conducted research on similar topics.
In summer of 2023, I completed my PhD in Computer Science (AI/Interactive Systems) at the University of Michigan under Prof. Emily Provost as part of the CHAI group.
Tl;dr: I work in the area of developing interpretable and human imitating evaluation and cost-effective data collection procedures, that feed back into model training and fine-tuning docussing on developing robust and responsible AI systems.
Other than research, I am interested in science communication, sketchnoting, personal knowledge management and cooking. One of my favorite activities during international conferences is to plan every single meal.
I love cats, and they keep me sane. I have two: Oreo and Bert (yes, that Bert, you read it right!).
Research Interests
Education
PhD in Computer Science and Engineering
Advisor(s): Prof. Emily Provost
MS in Computer Science and Engineering
Advisor(s): Prof. Emily Provost
BTech in Computer Engineering
Advisor(s): Prof. G.L. Prajapati
Experience
-
Member of Technical Staff - Research Scientist, Norm AI
Retrieval Augmentation in LLMs and their evaluation
-
Research Intern, Allen NLP, Allen Institute of Artificial Intelligence
Mentor(s) : Ana Marasović
Benchmarking interpretable and compositional evaluation for very large models in natural language processing
-
Research Intern, NLP Team, Facebook AI Research (Meta AI)
Mentor(s) : Adina Williams; Scott Yih, Pedro Rogieruez
Identifying, understanding, and correcting ambiguity based faliure points in Natural Language Inference (NLI)
-
Research Intern, Conversation AI, Facebook (Meta) AI
Mentor(s) : Ahmad Beirami, Shane Moon, Satwik Kottur, Chinnadhurai Sankar
Defining interpretable and generalizable user satisfaction metric informed by human knowledge
-
Research Intern, SENTIC Lab, Nanyang Technological University, Singapore
Mentor(s) : Erik Cambria
Multimodal detection of human behavior: empathy and deception
-
Research Intern, NLP and Sentiment Analysis (NLPSA) Lab, Academia Sinica, Taiwan
Mentor(s) : Lun-Wei Ku
Human perception of conversation sentiment visualization in chat interfaces
-
Research Intern, Indraprastha Institute of Information Technology (IIIT), Delhi
Mentor(s) : Pravesh Biyani
Finding the optimal routes under user specified user-constraints for last mile cab-pooling