16 citations · 21 across the 11 of their papers we have counts for
11 papers
BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?
Soumadeep Saha, Krish Sharma, Akshay Chaturvedi +1
Although reinforcement learning with verifiable rewards (RLVR) has improved the performance of large language models (LLMs) across a variety of reasoning tasks, there is significan…
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
Krish Sharma, Omar Naim, Soumadeep Saha +3
Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we investigate when such improvements…
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…
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…
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…
Deep Learning Based Recalibration of SDSS and DESI BAO Alleviates Hubble and Clustering Tensions
Rahul Shah, Purba Mukherjee, Soumadeep Saha +2
Conventional calibration of Baryon Acoustic Oscillations (BAO) data relies on estimation of the sound horizon at drag epoch from early universe observations by assuming a cos…
Language Models are Crossword Solvers
Soumadeep Saha, Sutanoya Chakraborty, Saptarshi Saha +1
Crosswords are a form of word puzzle that require a solver to demonstrate a high degree of proficiency in natural language understanding, wordplay, reasoning, and world knowledge,…
LADDER: Revisiting the Cosmic Distance Ladder with Deep Learning Approaches and Exploring its Applications
Rahul Shah, Soumadeep Saha, Purba Mukherjee +2
We investigate the prospect of reconstructing the ''cosmic distance ladder'' of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Dista…
VALUED -- Vision and Logical Understanding Evaluation Dataset
Soumadeep Saha, Saptarshi Saha, Utpal Garain
Starting with early successes in computer vision tasks, deep learning based techniques have since overtaken state of the art approaches in a multitude of domains. However, it has b…
DOST -- Domain Obedient Self-supervised Training for Multi Label Classification with Noisy Labels
Soumadeep Saha, Utpal Garain, Arijit Ukil +2
The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise. Although this issue has been widely discus…
Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering
Akshay Chaturvedi, Swarnadeep Bhar, Soumadeep Saha +2
Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in bo…