Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation

Zijian Ding, Alison Smith-Renner, Wenjuan Zhang, Joel R. Tetreault, Alejandro Jaimes

Submission Type: Regular Long Paper

Submission Track: Human-Centered NLP

Submission Track 2: Summarization

Keywords: human-centered NLP, large language model, human-AI collaboration, text summarization

TL;DR: We explored common human-AI interaction types in the context of LLM-assisted news headline generation.

Abstract: 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.

Submission Number: 1992