Syntax Error-Free and Generalizable Tool Use for LLMs: Appendix

Written by textmodels | Published 2024/06/02
Tech Story Tags: llms | tool-augmentation | syntax-errors | decoding-algorithm | finite-state-machine | tooldec | tool-selection | syntax-error-free

TLDRResearchers propose TOOLDEC, a finite-state machine-guided decoding for LLMs, reducing errors and improving tool use.via the TL;DR App

Authors:

(1) Kexun Zhang, UC Santa Barbara and Equal contribution;

(2) Hongqiao Chen, Northwood High School and Equal contribution;

(3) Lei Li, Carnegie Mellon University;

(4) William Yang Wang,UC Santa Barbara.

Table of Links

A. APPENDIX

A.1 PSEUDO-CODE OF THE DECODING ALGORITHM

A.2 GENERALIZING TOOLKENGPT TO UNSEEN NEW TOOLS

A.3 EXAMPLES OF TOOLDEC ELIMINATING TOOL-RELATED ERRORS

In this section, we show examples of TOOLDEC preventing tool-related errors on various baselines. Baselines are displayed in the left column and TOOLDEC is showed on the right.

Figure 7: TOOLDEC can prevent function name error, function argument error, and invalid ReAct syntax on ToolLLM.

A.4 EXAMPLES OF KAMEL RELATIONS

This paper is available on arxiv under CC 4.0 DEED license.


Written by textmodels | We publish the best academic papers on rule-based techniques, LLMs, & the generation of text that resembles human text.
Published by HackerNoon on 2024/06/02