AI RESEARCH
Learning the Error Patterns of Language Models
arXiv CS.AI
•
ArXi:2605.28328v1 Announce Type: cross When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused ways: for example, by using Python function names when generating TypeScript. We observe that these error patterns can be represented using a small number of constraints that can be learned in practice.