My current research interests lie at the intersection of Responsible AI and Cultural Psychology. I’m particularly interested in auditing and mitigating bias in large language models across demographic and cross-lingual contexts, and in understanding how AI assistance shapes human decision-making.

My past work spans Requirements Engineering, Legal AI, and Human-Computer Interaction, where I explored how LLMs can detect and resolve ambiguity, predict legal judgments, and how thoughtful design choices can improve collaboration between humans and AI systems in decision-making contexts.

Ongoing Work

1. RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models

A counterfactual audit of demographic bias in LLM-generated economic advice, spanning roughly 39,000 prompts and 87 India-specific identifiers in English and Hinglish. The study finds that advice shifts by about 20% under demographic perturbation alone.
Authors: Pavithra PM Nair, Bhavik Talaviya, Shourya Bhushan, Rahul Pankajakshan, Seema Guruvadoo, Avinash Agarwal, Gilad Gressel, Krishnashree Achuthan
Keywords: Bias Auditing, LLM Fairness, Economic Advice, Counterfactual Evaluation
Status: Under review

Published Work

For the most recent list, check out my Google Scholar.

1. “Sorry, Can’t Help You”: How Large Language Models Judge Failures to Help Across Languages

Pavithra PM Nair, Gilad Gressel, Krishnashree Achuthan
4th Workshop on Cross-Cultural Considerations in NLP (C3NLP), ACL 2026. Best Paper Award

2. From Regulation to Requirements: An Automated Requirement Derivation and Explanation Pipeline

Pavithra PM Nair, Preethu Rose Anish
34th IEEE International Requirements Engineering Conference (RE), Industrial Innovation Track, 2026.

3. Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements Using Multi-Level Domain Knowledge Bases

Pavithra PM Nair, Preethu Rose Anish
International Conference on Evaluation and Assessment in Software Engineering (EASE), 2026.

4. Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System

Pavithra PM Nair, Preethu Rose Anish
Artificial Intelligence and Law Workshop, AAAI 2026.

5. C-PASS: An Organization-centric Framework for Compliance and Penalty Assessment Using Large Language Models

Authors: Gokul Rejithkumar, Sachin Pawar, Pavithra PM Nair, Nitin Ramrakhiyani, Preethu Rose Anish
Information and Software Technology, 2026.

6. Lost in Translation? How Language Shapes Responsibility Attribution in Large Language Models

Pavithra PM Nair, Gilad Gressel, Krishnashree Achuthan
4th Workshop on Cross-Cultural Considerations in NLP (C3NLP), ACL 2026.

7. Sruthi: What Becomes Sayable Through Peer-Mode Reflective Scaffolding in Fieldwork Communication

Authors: Srividya Sheshadri, Manju Balakrishna Pillai, Renuka Kumar, Pavithra PM Nair, Apoorv Gupta, Megha TM, Sooraj S Nair, Balu Mohandas Menon, Unnikrishnan Radhakrishnan, Bhavani Rao R
ACM SIGCHI Conversational User Interfaces (CUI), 2026.

8. To Solicit or Not to Solicit? Impact of AI Assistance Delivery Mechanisms on Decision-Making

Pavithra PM Nair, Gilad Gressel, Malavika Nambrath Anand, Krishnashree Achuthan
International Journal of Human–Computer Interaction, 2025.
[Code]

9. An Integration of Indian Philosophy and Machine Learning for Human-like Cognition

Akhbar Sha, Anvita Reddy Inture, Jose Joseph, Pavithra PM Nair, MJ Sheeba, T Anjali
International Conference on Automation, Computing and Renewable Systems (ICACRS), 2023.