We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown our model’s critiques.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
We’ve applied reinforcement learning from human feedback to train language models that are better at summarization.
Scaling human oversight of AI systems for tasks that are difficult to evaluate.
arXiv:2605. 03202v2 Announce Type: replace Abstract: Large language models offer a tempting solution to address the peer review crisis.
arXiv:2606. 08000v1 Announce Type: cross Abstract: The progress of large language models (LLMs) has fueled claims that model-generated summaries rival or even surpass human-written references, raising questions about whether summarization remains an open research problem.
arXiv:2601. 14171v2 Announce Type: replace Abstract: Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details.
arXiv:2510. 26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values.