{"ID":2860541,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03743","arxiv_id":"2510.03743","title":"APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents","abstract":"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 .","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.03743","url_pdf":"https://arxiv.org/pdf/2510.03743v1","authors":"[\"Zachary Eberhart\",\"Collin McMillan\"]","published":"2025-10-04T08:58:49Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":608736,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2860541,"paper_url":"https://arxiv.org/abs/2510.03743","paper_title":"APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents","repo_url":"https://github.com/Zeberhart/apida-chat","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}