Jivnesh Sandhan

Postdoc Researcher

Graduate School of Informatics

Kyoto University, Japan.


Prospective Students: Please see the Contact Me page.
Languge Media Processing Lab
Office address : Building 9: S212
Research interest :
  • Computational Psychometrics for LLM
  • LLM Jailbreaking and Interpretability
  • Small language models
  • Animal Language Modeling
  • Sanskrit Computational Linguistics

Education :

  • Ph.D., Electrical Engineering, IIT Kanpur, India, 2023
  • M.S., Mathematics and Scientific Computing, IIT Kanpur, India, 2018
  • B.Tech., Mathematics and Scientific Computing, IIT Kanpur, India, 2017

Experience :

  • Postdoc Researcher, Kyoto University, Japan, (2024~2026) (QS World Ranking: 57)
    • Language Media Processing Lab, Graduate School of Informatics.
    • Supervisor: Prof. Yugo Murawaki
    • Research Area: LLM Computational Psychometrics, LLM Persona Jailbreaking and Interpretability
    • Publications at postdoc: CAPE (EMNLP25), Mahānāma (EMNLP25), ANVAYA (AACL25*), PHISH (EACL26*), MITRA (EACL26*)
  • Visiting Assistant Professor, IIT Dharwad, India (2023~2024)
    • Dept. of Computer Science, Excellent Teaching Feedback
    • Courses Taught at IITDh: Computer Programming (CS101), Artificial Intelligence (CS201) and Indian Knowledge System (IKS2)
    • Research Area: Image Caption Evaluation, Computational Cultural Linguistics, Low-resource Multi-lingual NLP
    • Publications at IITDh: TAGSIM (ICIP25), BharatBhasha (AACL25*), CSSL (EMNLP24) and DepNeCTI (EMNLP23)

Brief Bio :

Dr. Jivnesh Sandhan is a postdoctoral researcher at the Graduate School of Informatics, Kyoto University. Prior to this, he served as a Visiting Assistant Professor in the Department of Computer Science at the IIT Dharwad. He earned his Ph.D. from the Department of Electrical Engineering at IIT Kanpur in 2023, following a dual degree (B.Tech–M.Tech) in Mathematics and Scientific Computing from the same institution in 2018. He is a recipient of the prestigious Prime Minister's Research Fellowship (PMRF). His current research focus is on understanding and modeling the behavioral consistency of Large Language Models (LLMs) through the lens of Computational Psychometrics. His broader research interests include LLM Jailbreaking and Interpretability, Small Language Models, Animal Language Modeling and Sanskrit Computational Linguistics. He is particularly interested in how LLMs can be evaluated, aligned, and trusted in real-world, context-sensitive settings.

News:

  • November 4th, 2025: I received the Outstanding Area Chair Award at EMNLP 2025.
  • October 26th, 2025: Our ''Still Not There!'' paper got accepted into AACL-IJCNLP25 (mains).
  • September 17th, 2025: Our Mahānāma paper got nominated for the best Resource Paper Award at EMNLP25.
  • August 21st, 2025: Our 2 papers (Mahānāma and CAPE) got accepted into EMNLP25.
  • July 30th, 2025: I will be serving as a Area Chair for AACL25 (ARR25: July cycle).
  • July 20th, 2025: Program committee member for AACL25 (BHASHA workshop).
  • June 25th, 2025: I will be serving as a Area Chair for EMNLP25 (ARR25: May cycle).
  • May 21st, 2025: Our TAGSIM paper got accepted in ICIP25.
  • May 19th, 2025: I will be serving as a reviewer for ARR25 (May cycle).
  • March 16th, 2025: Our paper got accepted in WSC25.
  • Feburary 15th, 2025: I will be serving as a reviewer for ARR25 (February cycle).
  • January 1st, 2025: I will be serving as programme committee member for WSC25.
  • December 2nd, 2024: I joined as a postdoc at Kyoto University.
  • September 20th, 2024: Our CSSL paper got accepted in EMNLP24 main track.
  • October 31th, 2023: I joined as a visiting assistant professor at IIT Dharwad.
  • August 16th, 2023: I defended my Ph.D. thesis.
  • October 8th, 2023: Our paper, DepNECTI got accepted in EMNLP'23 (Findings).
  • May 8th, 2023: Our paper, SanskritShala got accepted in ACL'23 (System Demonstrations).