Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer
Year: 2026
Type: preprint
Abstract: Structured-output benchmarks reward both task decisions and interface compliance, so prompt-induced function-calling gains require attribution before they can be interpreted as transferable skill. We introduce a four-layer gain-attribution protocol for prompt-prepended skill injection, combining canonicalized rescoring, format-only controls, repaired/balanced induction, and portability checks. Applied to the Berkeley Function Calling Leaderboard (BFCL) and scoped with API-Bank, MATH-500, and MultiHop-RAG, the protocol shows that several apparent gains are better attributed to interface alignment than to procedural transfer: format-only prompts match or exceed full skills in key BFCL cells, repaired/balanced induction removes the largest sub-frontier gains, and API-Bank target-native gains are matched within 0.5 percentage points (pp) by length-matched generic procedural prompts. These findings treat format compliance as a useful engineering capability while clarifying what a structured-output score certifies. We release BFCL-CANONICAL and recommend canonicalized metrics, balanced induction, and format-only baselines for function-calling skill-gain attribution. Code and data are available at https://github.com/couragec/skill-injection-attribution.
Source: arXiv (Cornell University)
Authors: Chen, Wanyi, Chen, Daoyuan, Kong, Fang
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7167602115
Cites:
Cited by:
Related to: