Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
Chakrabarty, Tuhin, Laban, Philippe, Wu, Chien-Sheng
–arXiv.org Artificial Intelligence
LLM-based applications are helping people write, and LLM-generated text is making its way into social media, journalism, and our classrooms. However, the differences between LLM-generated and human-written text remain unclear. To explore this, we hired professional writers to edit paragraphs in several creative domains. We first found these writers agree on undesirable idiosyncrasies in LLM-generated text, formalizing it into a seven-category taxonomy (e.g. cliches, unnecessary exposition). Second, we curated the LAMP corpus: 1,057 LLM-generated paragraphs edited by professional writers according to our taxonomy. Analysis of LAMP reveals that none of the LLMs used in our study (GPT4o, Claude-3.5-Sonnet, Llama-3.1-70b) outperform each other in terms of writing quality, revealing common limitations across model families. Third, we explored automatic editing methods to improve LLM-generated text. A large-scale preference annotation confirms that although experts largely prefer text edited by other experts, automatic editing methods show promise in improving alignment between LLM-generated and human-written text.
arXiv.org Artificial Intelligence
Sep-25-2024
- Country:
- Asia (1.00)
- Europe (1.00)
- North America > United States
- Massachusetts > Suffolk County
- Boston (0.14)
- Washington > King County
- Seattle (0.14)
- Massachusetts > Suffolk County
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Education
- Curriculum > Subject-Specific Education (0.45)
- Educational Setting (0.46)
- Health & Medicine
- Consumer Health (0.46)
- Therapeutic Area (0.67)
- Leisure & Entertainment (0.67)
- Media (0.66)
- Education
- Technology: