Postdoctoral Scholar at Ohio State University; affiliated with OSU NLP
Email: lal.77 <at> osu <dot> edu
Hi! I'm a postdoc at Ohio State University advised by Huan Sun and Yu Su. I am working on advancing the reliability and safety of computer-use agent (CUA) plans.
I earned my PhD at Stony Brook University, advised by Niranjan Balasubramanian. My primary research focused on evaluating and improving the abilities of NLP models to understand and use causal knowledge about narratives and plans. I collaborated extensively with Nate Chambers and Ray Mooney on this line of work.
I also worked on understanding how well large language models (LLMs) understand the social and personal aspects of reasoning expressed in language, working with H. Andrew Schwartz.
Started my postdoc at OSUNLP with Huan Sun and Yu Su.
I defended my PhD, with my thesis titled "Using Causal Knowledge to Improve Reasoning in Narratives and Plans".
Long paper accepted to AACL 2025.
Presented CaT-Bench at the NYC ML Symposium organized by the New York Academy of Sciences.
Long paper accepted to EMNLP, 2024. I am also co-organizing WNU 2024. I'll be attending in-person. See you in sunny Miami!
Paper from my AI2 Internship accepted to ACL (Findings), 2024. I will be presenting it at the NLRSE workshop. See you in Bangkok!
Paper from my Google Research Internship accepted to TrustNLP workshop collocated with NAACL, 2024. I'll be presenting in Mexico City!
Short paper accepted to EACL, 2024.
I am spending the Fall semester at Google Research with the Responsible, Application-Driven Machine Learning (RADML) team in the Responsible AI and Human Centered Technology (RAI-HCT) org working with Ananth Balashankar, Ahmad Beirami and Preethi Lahoti.
Short paper accepted to ACL, 2023. Another accepted to a workshop (WASSA). My co-authors will be presenting in Toronto!
I am spending the summer at Allen Institute for Artificial Intelligence in the Aristo team working with Niket Tandon.
Long paper accepted to EMNLP, 2022. I'll be attending in-person. See you in Abu Dhabi!
I am spending the summer working on question decomposition for multi-hop question answering at Salesforce Research with Semih Yavuz and Yingbo Zhou.
Two papers accepted at ACL, 2021 --- one in main conference, one in Findings