Learning the Error Patterns of Language Models 事件

Learning the Error Patterns of Language Models arXiv:2605.28328v1 Announce Type: cross Abstract: 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. We propose \emph{prefix filters}, which are per-d