A new 109-conversation, 86-API benchmark for LLM function-calling in multi-turn dialogue shows top models at about 40% accuracy and near-zero performance on chains of 4+ calls.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions
A new 109-conversation, 86-API benchmark for LLM function-calling in multi-turn dialogue shows top models at about 40% accuracy and near-zero performance on chains of 4+ calls.