Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation
This addresses the problem of optimizing human-AI collaboration in writing tasks for users like journalists or content creators, but it is incremental as it builds on existing interaction methods.
The study tackled how humans can effectively use LLMs for news headline generation, finding that human control is necessary to fix undesirable outputs, with guiding and selecting model outputs providing the most benefit at the lowest cost.
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.