2 papers
cs.LG2026
The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning
Amrut Nadgir, Pratik Chaudhari, Vijay Balasubramanian
We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when data is structured such tha…
cs.LG2026
How does Chain of Thought decompose complex tasks?
Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari
Many language tasks can be modeled as classification problems where a large language model (LLM) is given a prompt and selects one among many possible answers. We show that the cla…