Pavan Chakraborty

Papers on Lattice

Total citations

Topics

h-index

Research focus

Eval Frameworks & Benchmarks (3)Red-Teaming & Adversarial Robustness (2)Interpretability & Mechanistic Interp (1)Reasoning & Chain-of-Thought (1)Constitutional AI & AI Ethics (1)Scientific Discovery & Drug Design (1)

Frequent co-authors

Abhinaba Basu (3)Abhinaba Basu (2)Pavan Chakraborty (2)

Papers (3)

Mar 19, 2026

Abhinaba Basu +3Mar 19, 2026·also Indian Institute of Information Technology, National Institute of Electronics and Information

ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs

LLM explanation faithfulness varies wildly depending on how you test it, and might even be *anti*-faithful, so stop relying on single-intervention benchmarks.

Abhinaba Basu, Abhinaba Basu, Pavan Chakraborty +1

Eval Frameworks & Benchmarks Interpretability & Mechanistic Interp Reasoning & Chain-of-Thought

Abhinaba Basu +3Mar 19, 2026·also Indian Institute of Information Technology, National Institute of Electronics and Information

When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making

LLMs are far more susceptible to authority and framing biases than the field's obsession with demographic bias suggests.

Abhinaba Basu, Abhinaba Basu, Pavan Chakraborty +1

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Mar 12, 2026

Abhinaba Basu +1Mar 12, 2026

Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials

Machine-learned interatomic potentials miss 93% of stable materials, but a new auditing framework closes this gap and boosts discovery yield by 25%.

Abhinaba Basu, Pavan Chakraborty

Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness Scientific Discovery & Drug Design

Pavan Chakraborty

Research focus

Frequent co-authors

Papers (3)

Search

Pavan Chakraborty

Research focus

Frequent co-authors

Papers (3)