Learning and Enforcing Context-Sensitive Control for LLMs

arXiv:2604.10667v1 Announce Type: cross Abstract: Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such constraints typically require manual specification -- a significant barrier demanding specialized expertise. We introduce a framework that automatically learns context-sensitive constraints from LLM interactions through a two-phase process: syntactic exploration to gather diverse outputs for constraint learning, followed by constraint exploitation to enforce these learned rules during generation. Experiments demonstrate that our method enables even small LLMs (1B parameters) to learn and generate with perfect constraint adherence, outperforming larger counterparts and state-of-the-art reasoning models. This work represents the first integration of context-sensitive grammar learning with LLM generation, eliminating manual specification while maintaining generation validity.

Related

• Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?
• Learning is Forgetting: LLM Training As Lossy Compression
• A Comparative Theoretical Analysis of Entropy Control Methods in Reinforcement Learning
• A Mechanistic Analysis of Looped Reasoning Language Models
• SkillFactory: Self-Distillation For Learning Cognitive Behaviors

Source: arXiv cs.AI | 2026-04-14