← all papers · overview

Don't Fine-tune, Decode: Syntax Error-free Tool Use Via Constrained Decoding

Abstract

Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-tuning and prompting can mitigate the issue, these approaches are expensive and hard to generalize. Furthermore, because syntax constraints are only learned implicitly during fine-tuning, models still make frequent syntax

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).