Scholar
Inderjeet Nair
Google Scholar ID: _C4CkDEAAAAJ
University of Michigan
Citations & Impact
Citations
64
H-index
5
i10-index
2
Publications
20
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions' accepted to EMNLP 2024 (Oral)
- Paper 'MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning' accepted to ACL 2024 (Oral), awarded Area Chair Award
- Paper 'Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering' accepted to EMNLP 2023 Findings
- Co-authored 'Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction' accepted to ACL 2023 Workshop RepL4NLP
- Preprints include 'Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths' and 'ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists'
Background
- Third-year Ph.D. candidate at the University of Michigan, Ann Arbor, advised by Prof. Lu Wang
- Broad research interests in Machine Learning, Natural Language Processing (NLP), and related fields
- Currently investigating deceptive and scheming behaviors that may emerge in language models during alignment
- Exploring the generation of complex function/API calling data points using LLMs to improve and evaluate tool-use capabilities
- Previously worked on applications of LLMs in education, structured commonsense reasoning, and consistency evaluation of value preferences
