arXiv cs.AI· Michela Taufer, Kin Ng, Ian Lumsden, Aashish Pandey, Rajasi Gore, Angelina Ju, Sukanya Moudgalya, Ewa Deelman, Sai Swaminathan·· 2 小时前AI 评分30
HAIDL：将人机交互作为一等数据的可解释 AI 协作形式化模型与运行时
Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration
AI 导读
研究者提出人机交互描述语言 HAIDL，用类 Backus-Naur 形式的语法把每次人机交互编码为包含计算上下文、用户请求、提示词、AI 响应、反馈、来源和模型元数据的结构化对象，使交互成为可复用数据而非瞬时的提示-响应交换。
正文 · 原文
Abstract:AI assistants are increasingly embedded in computational notebooks, scientific workflows, software engineering tools, and learning systems, yet human-AI interactions are often treated as transient prompt-response exchanges rather than durable data products, hindering reproducibility, explainability, replay, behavioral analysis, and adaptive AI support. We argue that these interactions form a new data class requiring formal representation and introduce the Human-AI Interaction Description Language (HAIDL), a formal interaction model with a Backus-Naur Form-inspired concrete syntax. HAIDL encodes each interaction as a structured object capturing computational context, user request, prompt payload, AI response, feedback, problem context, provenance, and model metadata. We integrate this vision into HAIDL-X, a middleware for JupyterLab that instantiates HAIDL by capturing user-bot state, building contextualized prompts, interfacing with AI providers, collecting feedback, and storing interactions in a repository. We add a learning layer over HAIDL that maps interaction objects and notebook execution traces into reproducible measures of user behavior, including engagement, performance, help-seeking, error-oriented use, and learning personas. HAIDL-X provides a foundation for treating human-AI collaboration as structured, queryable, replayable, analyzable data.
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.40006 [cs.AI] |
| (or arXiv:2610.40006v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40006 arXiv-issued DOI via DataCite |
Submission history
From: Kin Ng [view email]
[v1]
Thu, 29 Oct 2026 13:23:54 UTC (2,844 KB)
来源：arXiv cs.AI · arxiv.org