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
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.
BibTeX
@inproceedings{
ding2023harnessing,
title={Harnessing the power of {LLM}s: Evaluating human-{AI} text co-creation through the lens of news headline generation},
author={Zijian Ding and Alison Smith-Renner and Wenjuan Zhang and Joel R. Tetreault and Alejandro Jaimes},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=pPiJykFn0K}
}