SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
Mark Russinovich, Ahmed Salem, and Ronen Eldan
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
LLMs show instruction-following rates from 1% to 99% when instructions conflict with hardcoded pattern demonstrations, with output diversity as the main predictor of resistance.
citing papers explorer
-
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
-
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
LLMs show instruction-following rates from 1% to 99% when instructions conflict with hardcoded pattern demonstrations, with output diversity as the main predictor of resistance.