A reliability alignment framework, Relign, that expands the LLM tool-use action space with indecisive actions reduces tool hallucination rates and improves task success on the new RelyToolBench benchmark.
Large Language Models as Tool Makers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reducing Tool Hallucination via Reliability Alignment
A reliability alignment framework, Relign, that expands the LLM tool-use action space with indecisive actions reduces tool hallucination rates and improves task success on the new RelyToolBench benchmark.