activity
20242026
collaborators

6 papers

cs.AI2026

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape

Amartya Roy, Sonali Parbhoo

Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perform it reliably remains an open question. Recent benchmarks show that even fine…

cs.LG2026

The -Combinator for LLMs: Solving Long-Context Rot with -Calculus

Amartya Roy, Rasul Tutunov, Xiaotong Ji +2

LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs) address this by externalisi…

cs.CL2025

Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models

Amartya Roy, Elamparithy M, Kripabandhu Ghosh +2

In context learning (ICL) underpins recent advances in large language models (LLMs), although its role and performance in causal reasoning remains unclear. Causal reasoning demands…

cs.LG2025

Competition is the key: A Game Theoretic Causal Discovery Approach

Amartya Roy, Souvik Chakraborty

Causal discovery remains a central challenge in machine learning, yet existing methods face a fundamental gap: algorithms like GES and GraN-DAG achieve strong empirical performance…

cs.LG2025

Guide: Generalized-Prior and Data Encoders for DAG Estimation

Amartya Roy, Devharish N, Shreya Ganguly +1

Modern causal discovery methods face critical limitations in scalability, computational efficiency, and adaptability to mixed data types, as evidenced by benchmarks on node scalabi…

cs.CL2024

On the effective transfer of knowledge from English to Hindi Wikipedia

Paramita Das, Amartya Roy, Ritabrata Chakraborty +1

Although Wikipedia is the largest multilingual encyclopedia, it remains inherently incomplete. There is a significant disparity in the quality of content between high-resource lang…