Basic Information

Email Address

• Email Address

  sandhan.jivnesh.6zkyoto-u.ac.jp

Academic Degree

• 30 Apr. 2018

  Master's degree(Indian Institute of Technology，Kanpur)
• 16 Aug. 2023

  Ph.D(Indian Institute of Technology，Kanpur)

Academic Resume (Undergraduate School/Majors)

• Narayana College，Hyderabad(India), (SUBJECT: Maths，Physics，Chemistry，English，Sanskrit), 卒業

ID,URL

• J-Global ID

  202601010104011883

researchmap URL

• https://researchmap.jp/jivnesh

Research

Research Topics, Overview of the research

• Research Topics

  LLM Psychometrics and Jailbreaking, AI for Social Good, Computational Linguistics

• Overview of the research

  My work focuses on building Human-Centric AI that is reliable, culturally aware, and genuinely useful in the
  real world. In my Ph.D., I created deep-learning tools that open access to Sanskrit knowledge by preserving its
  linguistic structure. In my postdoctoral work, I shifted to LLM psychometrics, where I uncovered major gaps in
  the behavioral stability and safety of modern LLMs, including the first evidence that a model’s persona can be
  manipulated through conversation alone. These experiences shaped my larger vision: to build AI systems that
  expand access to knowledge, support society in high-impact domains like healthcare and scientific review, and
  help us understand intelligence itself, whether in humans or machines.

Research Interests

• NLP, LLM Psychometrics, LLM Interpretability, LLM Jailbreaking

Papers

• Can We Trust LLM Detectors?

  Jivnesh Sandhan; Harshit Jaiswal; Fei Cheng; Yugo Murawaki

  言語処理学会 第32回年次大会, Mar. 2026

  
• Persona Jailbreaking in Large Language Models

  Jivnesh Sandhan; Fei Cheng; Tushar Sandhan; Yugo Murawaki

  Proceedings of 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026): Findings Volume, Mar. 2026, Peer-reviewed

  
• Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?

  Kunal Kingkar Das; Manoj Balaji Jagadeeshan; Nallani Chakravartula Sahith; Jivnesh Sandhan; Pawan Goyal

  Proceedings of IJCNLP-AACL 2025 (Mains) : International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics, Dec. 2025, Peer-reviewed

  
• Mahānāma: A Unique Testbed for Literary Entity Discovery and Linking

  Sujoy Sarkar; Gourav Sarkar; Manoj Balaji Jagadeeshan; Jivnesh Sandhan; Amrith Krishna; Pawan Goyal

  Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Nov. 2025, Peer-reviewed

  
• CAPE: Context-Aware Personality Evaluation Framework for Large Language Models

  Jivnesh Sandhan; Fei Cheng; Tushar Sandhan; Yugo Murawaki

  Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025): Findings Volume, Nov. 2025, Peer-reviewed

  

Awards

• 03 Nov. 2025

  EMNLP25, Suzho, Finalist for Best Resource Paper Award, at EMNLP25, Suzho
• 05 Nov. 2025

  EMNLP25, Outstanding Area Chair Award, EMNLP25
• 17 Dec. 2022

  Recipient of the best poster award(IndoML Symposium 2022)
• 17 Dec. 2021

  The first position in the Morphological Parsing task at Hackathon(IIT Kharagpur)