Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
How Does RL Post-training Induce Skill Composition? A Case Study on Countdown
Simon Park, Simran Kaur, Sanjeev Arora
While reinforcement learning (RL) successfully enhances reasoning in large language models, its role in fostering compositional generalization (the ability to synthesize novel skil…
cs.LG2025
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
Simran Kaur, Simon Park, Anirudh Goyal +1
We introduce Instruct-SkillMix, an automated approach for creating diverse, high quality SFT data for instruction-following. The pipeline involves two stages, each leveraging an ex…