Methodological reflections for AI alignment research using human feedback

December 22, 2022 Β· Declared Dead Β· πŸ› arXiv.org

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Thilo Hagendorff, Sarah Fabi arXiv ID 2301.06859 Category cs.HC: Human-Computer Interaction Cross-listed cs.AI, cs.CL, cs.LG Citations 11 Venue arXiv.org Last Checked 4 months ago
Abstract
The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models (LLMs), which have the potential to exhibit unintended behavior due to their ability to learn and adapt in ways that are difficult to predict. In this paper, we discuss methodological challenges for the alignment problem specifically in the context of LLMs trained to summarize texts. In particular, we focus on methods for collecting reliable human feedback on summaries to train a reward model which in turn improves the summarization model. We conclude by suggesting specific improvements in the experimental design of alignment studies for LLMs' summarization capabilities.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted