To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e.g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation. While LLMs alone can generate satisfactory news headlines, on average, human control is needed to fix undesirable model outputs. Of the interaction methods, guiding and selecting model output added the most benefit with the lowest cost (in time and effort). Further, AI assistance did not harm participants' perception of control compared to freeform editing.

翻译：为探究人类如何最佳利用大语言模型进行写作，以及人机交互如何影响写作过程中的所有权感知与信任度，本研究在基于大语言模型辅助的新闻标题生成任务中，比较了常见的人机交互模式（如系统引导、输出内容筛选、输出后编辑）。研究发现：虽然大语言模型能独立生成令人满意的新闻标题，但通常需要人工介入以修正不符合预期的模型输出。在各类交互模式中，引导与筛选模型输出能以最低时间与精力成本实现最大效益。此外，与自由编辑模式相比，人工智能辅助并未削弱参与者对写作过程的主导感知。