Inkit Padhi

Computer Science · Physical Sciences

15h-index1.3kcitations58works1.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(14), Computational Drug Discovery Methods(10), Machine Learning in Materials Science(10), Natural Language Processing Techniques(9), Multimodal Machine Learning Applications(8)

Publications58 total

When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2025Open Access
Contextual Value Alignment
2025
Granite Guardian: Comprehensive LLM Safeguarding
2025· 2 citedOpen Access
Granite Guardian
arXiv (Cornell University)·2024Open Access
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
arXiv (Cornell University)·2024Open Access
Programming Refusal with Conditional Activation Steering
arXiv (Cornell University)·2024Open Access
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
IEEE Internet Computing·2024· 4 cited
Value Alignment from Unstructured Text
arXiv (Cornell University)·2024Open Access
PCAN: A Pandemic-Compatible Attentive Neural Network for Retail Sales Forecasting
2024· 2 citedOpen Access
When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
arXiv (Cornell University)·2024Open Access
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
arXiv (Cornell University)·2024· 1 citedOpen Access
Contextual Moral Value Alignment Through Context-Based Aggregation
arXiv (Cornell University)·2024· 1 citedOpen Access
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
arXiv (Cornell University)·2024· 2 citedOpen Access
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
arXiv (Cornell University)·2024Open Access
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
2024
Value Alignment from Unstructured Text
2024Open Access
Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
IEEE Journal on Emerging and Selected Topics in Circuits and Systems·2024· 7 citedOpen Access
The incentive gap in data work in the era of large models
Nature Machine Intelligence·2023· 7 cited
The Impact of Positional Encoding on Length Generalization in Transformers
arXiv (Cornell University)·2023· 33 citedOpen Access
Accelerating material design with the generative toolkit for scientific discovery
npj Computational Materials·2023· 33 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Pierre Dognin(26), Payel Das(20), Vijil Chenthamarakshan(15), Youssef Mroueh(15), Igor Melnyk(15), Prasanna Sattigeri(13), Brian Belgodere(10), Kush R. Varshney(10), Cícero Nogueira dos Santos(9), Manish Nagireddy(9), Mattia Rigotti(8), Yair Schiff(8), Jerret Ross(7), Aleksandra Mojsilović(6), Karthikeyan Natesan Ramamurthy(6), Hendrik Strobelt(5), Jarret Ross(5), Kahini Wadhawan(5), Elizabeth Daly(5), Samuel C. Hoffman(4)