activity
20242026
collaborators

8 papers

cs.CL2026

KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?

Soumadeep Saha, Akshay Chaturvedi, Saptarshi Saha +2

Chain-of-thought (CoT) traces have been shown to improve performance of large language models on a plethora of reasoning tasks, yet there is no consensus on the mechanism by which…

cs.AI2026

Cyclic Counterfactuals under Shift-Scale Interventions

Saptarshi Saha, Dhruv Vansraj Rathore, Utpal Garain

Most counterfactual inference frameworks traditionally assume acyclic structural causal models (SCMs), i.e. directed acyclic graphs (DAGs). However, many real-world systems (e.g. b…

cs.CL2025

sudoLLM: On Multi-role Alignment of Language Models

Soumadeep Saha, Akshay Chaturvedi, Joy Mahapatra +1

User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this…

stat.ML2025

On Measuring Intrinsic Causal Attributions in Deep Neural Networks

Saptarshi Saha, Dhruv Vansraj Rathore, Soumadeep Saha +2

Quantifying the causal influence of input features within neural networks has become a topic of increasing interest. Existing approaches typically assess direct, indirect, and tota…

astro-ph.IM2025

Square Kilometre Array Science Data Challenge 3a: foreground removal for an EoR experiment

A. Bonaldi, P. Hartley, R. Braun +179

We present and analyse the results of the Science data challenge 3a (SDC3a, https://sdc3.skao.int/challenges/foregrounds), an EoR foreground-removal community-wide exercise organis…

cs.CL2025

Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation

Joy Mahapatra, Soumyajit Roy, Utpal Garain

Monitoring factual inconsistency is essential for ensuring trustworthiness in data-to-text generation (D2T). While large language models (LLMs) have demonstrated exceptional perfor…