Inkit Padhi

Researcher, IBM Research

Joined

September 2018

Names

Inkit Padhi (Preferred)

Emails

****@gmail.com (Confirmed)

****@ibm.com (Confirmed)

Personal Links

Google Scholar

DBLP

ACL Anthology

Career & Education History

Researcher

IBM Research (ibm.com)

2016 – 2026

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
Abinitha Gourabathina, Inkit Padhi, Manish Nagireddy, Subhajit Chaudhury, Prasanna Sattigeri
- ACL '26 [to appear]
- Readers: Everyone
Chain-of-Thought Degrades Abstention in Large Language Models, Unless Inverted
Abinitha Gourabathina, Inkit Padhi, Manish Nagireddy, Subhajit Chaudhury, Prasanna Sattigeri
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Yue Huang, Hang Hua, Yujun Zhou, Pengcheng Jing, Manish Nagireddy, Inkit Padhi, Greta Dolcetti, Zhangchen Xu, Subhajit Chaudhury, Ambrish Rawat, Liubov Nedoshivina, Pin-Yu Chen, Prasanna Sattigeri, Xiangliang Zhang
- ICLR 2026 Poster
- Readers: Everyone
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
Dennis Wei, Inkit Padhi, Soumya Ghosh, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Maria Chang
- NeurIPS 2025 poster
- Readers: Everyone
Granite Guardian
Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Zahra Ashktorab, Inge Vejsbjerg, Elizabeth M. Daly, Michael Hind, Werner Geyer et al. (3 additional authors not shown)
- OpenReview Archive Direct Upload
- Readers: Everyone
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy, Amit Dhurandhar
- ICLR 2025 Spotlight
- Readers: Everyone
Value Alignment from Unstructured Text
Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, Kush R. Varshney
- Pluralistic-Alignment 2024
- Readers: Everyone
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
Swanand Kadhe, Farhan Ahmed, Dennis Wei, Nathalie Baracaldo, Inkit Padhi
- ICML 2024 FM-Wild Workshop Poster
- Readers: Everyone
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran T. Tchrakian, Radu Marinescu, Elizabeth M. Daly, Inkit Padhi, Prasanna Sattigeri
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
Influence Based Approaches to Algorithmic Fairness: A Closer Look
Soumya Ghosh, Prasanna Sattigeri, Inkit Padhi, Manish Nagireddy, Jie Chen
- NeurIPS XAIA 2023
- Readers: Everyone

View all 50 publications

Co-Authors

View all 120 co-authors