一句话：APIDA-Chat 用教师-学生蒸馏把符号对话脚本转成真实 API 搜索对话，低成本引导对话式智能体。
大语言模型助手擅长讲解流行 API，但在小众或专有库上表现不佳，因为多轮对话微调数据稀缺。本文提出 APIDA-Chat，一个开源流水线，将符号化对话行为脚本转换为真实、领域落地的 API 搜索对话。第一阶段用传统对话规划器配合高能力教师 LLM（o4-mini）合成金标准对话，并微调 Llama 3.2 3B 学生模型；第二阶段去掉教师，复用同一规划器与微调模型，实现低成本快速合成新对话且不将源码暴露给外部服务。评估显示，微调学生模型相比基座 BLEU 从 0.38 提升至 0.50，BERTScore 从 0.88 提升至 0.91，且完全可在单张消费级 GPU 上运行。所有组件模块化并公开，作为未来工作的保守基线。
Large-language-model assistants are suitable for explaining popular APIs, yet they falter on niche or proprietary libraries because the multi-turn dialogue data needed for fine-tuning are scarce. We present APIDA-Chat, an open-source pipeline that converts symbolic dialogue-act "scripts" into realistic, domain-grounded API Search conversations using a lightweight model for inexpensive training data generation. Phase I pairs a legacy dialogue planner with a high-capability teacher LLM (o4-mini) to synthesize a "gold set" of realized dialogues; then, a smaller Llama 3.2 3B student model is fine-tuned on this corpus. Phase II drops the teacher and reuses the same planner with the fine-tuned model, allowing rapid, low-cost synthesis of new dialogues without exposing source code to external services. The fine-tuned student improves BLEU from 0.38 to 0.50 and BERTScore from 0.88 to 0.91 versus the base model while running entirely on a single consumer GPU. All components are modular and publicly released to serve as a conservative baseline for future work. APIDA-Chat is open-sourced at https://github.com/Zeberhart/apida-chat and a video demo is available at https://youtu.be/YqmZBHyGbPs.
DOI 原文 ·
@inproceedings{paperbot9209,
title = {APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents},
author = {Zachary Eberhart and Collin McMillan},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00382}
}