activity
20242026
collaborators

9 papers

cs.CL2026

Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning

Saptarshi Sengupta, Suhang Wang

Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than large language models (LLMs…

cs.LG2026

GaLoRA: Parameter-Efficient Graph-Aware LLMs for Node Classification

Mayur Choudhary, Saptarshi Sengupta, Katerina Potika

The rapid rise of large language models (LLMs) and their ability to capture semantic relationships has led to their adoption in a wide range of applications. Text-attributed graphs…

cs.CL2026

ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers

Saptarshi Sengupta, Zhengyu Zhou, Jun Araki +4

Tool calling has become increasingly popular for Large Language Models (LLMs). However, for large tool sets, the resulting tokens would exceed the LLM's context window limit, makin…

cs.CL2025

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs

Jaydip Sen, Saptarshi Sengupta, Subhasis Dasgupta

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding…

cs.CL2025

BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

Saptarshi Sengupta, Shuhua Yang, Paul Kwong Yu +2

Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedicated to retrieving single modal…

cs.CL2025

MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification

Saptarshi Sengupta, Harsh Vashistha, Kristal Curtis +4

Extending the capabilities of Large Language Models (LLMs) with functions or tools for environment interaction has led to the emergence of the agent paradigm. In industry, training…