Hi it's me Sushrita!

Hello! My name is Sushrita Rakshit (pronounced suh-shree-tah). I am a senior at the University of Michigan, where I am advised by David Jurgens at the BLABLABLAB. Previously, I was part of the Affective Computing Group at the University of Southern California, where I was advised by Jonathan Gratch.

My primary research interests lie in ① exploring human behavior and ② Theory of Mind and behavior of large language models (LLMs), both fields that sit at the intersection of human-centered NLP and cognitive science. I am deeply passionate about advancing trustworthy human-centered AI systems that align with human values and cognitive processes. To achieve this, I employ a range of empirical methods to assess the strengths and limitations of these models. In the long run, I aim for my work to interpret social behaviors and match behavioral patterns when interacting with humans.

🗣️ I'm currently seeking positions for data-driven research and software engineering roles. Big plus if they are AI-oriented. Please reach out if my work interests you!

🗣️ I'll be on the program committee for ICLR 2025's Bi-Align Workshop! So excited to help facilitate this!

Legend:

C = Conference, J = Journal, W = Workshop, P = In Review

e.g., C.P.1 denotes Conference submission in review.

[C.P.1] Sushrita Rakshit¹, James Hale², Kushal Chawla³, Jeanne Brett⁴, Jonathan Gratch⁵ (2024). Towards Emotionally-Aware Agents for Dispute Resolution. Manuscript submitted to AAMAS 2025.

[C.2] James Anthony Hale¹, Sushrita Rakshit², Kushal Chawla³, Jeanne Brett⁴, Jonathan Gratch⁵ (2024). KODIS: A Multicultural Dispute Resolution Dialogue Corpus. Manuscript accepted to main conference at NAACL.

[J.P.1] Hua Shen¹, Tiffany Knearem², Reshmi Ghosh², Kenan Alkiek³, Kundan Krishna³, Yachuan Liu³, Ziqiao Ma³, Savvas Petridis³, Yi-Hao Peng³, Li Qiwei³, Sushrita Rakshit³, Chenglei Si³, Yutong Xie³, Jeffrey P. Bigham⁴, Frank Bentley⁴, Joyce Chai⁴, Zachary Lipton⁴, Qiaozhu Mei⁴, Rada Mihalcea⁴, Michael Terry⁴, Diyi Yang⁴, Meredith Ringel Morris⁵, Paul Resnick⁵, David Jurgens⁵ (2024). Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions. arXiv preprint, arXiv:2406.09264. Manuscript submitted to ACM CSUR.

[C.P.2] Jonathan Ivey¹, Shivani Kumar¹, Jiayu Liu¹, Hua Shen¹, Sushrita Rakshit¹, Rohan Raju¹, Haotian Zhang¹, Aparna Ananthasubramaniam¹, Junghwan Kim¹, Bowen Yi¹, Dustin Wright¹, Abraham Israeli¹, Anders Moller¹, Lechen Zhang¹ (2024). Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue. Manuscript Submitted to NAACL. Note: the authorship order is first author randomized.

[C.1] Yinuo Xu¹, Sushrita Rakshit¹, Aparna Ananthasubramaniam¹, Omkar Yadav¹, Mingqian Zheng¹, Michael Jiang¹, Lechen Zhang¹, Bowen Yi¹, Kenan Alkiek¹, Abraham Israeli¹, Bangzhao Shu¹, Hua Shen¹, Jiaxin Pei¹, Haotian Zhang¹, Miriam Schirmer¹, David Jurgens¹ (2024). Please Reply: Causally Modeling the Linguistic and Social Factors that Predict Email Response. Manuscript accepted to main conference at NAACL. Note: the authorship order is first author randomized.