Fine-tuning GPT-2 from human preferences
6y
Age
- Published
- Collected
We’ve fine-tuned the 774M parameter GPT-2 language model using human feedback for various tasks, successfully matching the preferences of the external human labelers, though those preferences did not always match our own. Specifically, for summarization tasks the labelers preferred sentences copied wholesale from the input (we’d only asked them to ensure accuracy), so our models learned to copy. Summarization required…
overfeed.news indexes and links. We publish a short excerpt — the full article stays at OpenAI News.
More from OpenAI News
Log in to follow this sourceBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking training
A randomized study of more than 1,000 students examines ChatGPT, critical thinking, originality, and student performance on a real-world university assignment.
Expanding OpenAI’s presence in Brazil
OpenAI is expanding its presence in Brazil, deepening engagement with developers, businesses, and communities to support AI adoption across the country.
Learning never stops: How AI makes learning continuous
OpenAI’s new report explores how students and educators use ChatGPT to make learning more continuous, with support that extends beyond the classroom.
Bringing ChatGPT for Teachers to more U.S. school districts
ChatGPT for Teachers is expanding to 55 U.S. school systems, bringing secure AI tools, training, and support to over 100,000 more educators and staff.