Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
Adam Younsi, Ahmed Attia, Abdalgader Abubaker +3
Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate…
cs.LG2025
PORT: Preference Optimization on Reasoning Traces
Salem Lahlou, Abdalgader Abubaker, Hakim Hacid
Preference optimization methods have been successfully applied to improve not only the alignment of large language models (LLMs) with human values, but also specific natural langua…