works on
mathematical reasoning 1model probing 1reinforcement learning 1representation analysis 1supervised fine-tuning 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models

Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit +2

The paper investigates why reinforcement‑learning‑trained models outperform supervised fine‑tuned models on math reasoning by analyzing their internal representations with linear p…