5 papers
Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch
Rima Hazra, Sayan Layek, Somnath Banerjee +2
We present Crase, a bounded and inspectable alternative to deep research agents for scholarly search. Instead of an open-ended search loop, Crase queries a search engine once for s…
Efficient Continual Pre-training of LLMs for Low-resource Languages
Arijit Nag, Soumen Chakrabarti, Animesh Mukherjee +1
Open-source Large Language models (OsLLMs) propel the democratization of natural language research by giving the flexibility to augment or update model parameters for performance i…
How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning
Subhabrata Dutta, Joykirat Singh, Soumen Chakrabarti +1
Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanis…
Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs
Arijit Nag, Animesh Mukherjee, Niloy Ganguly +1
Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). A few of them have been trained on low-resource l…
Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
Gurusha Juneja, Subhabrata Dutta, Soumen Chakrabarti +2
Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex,…