Ben Mann

2 papers in our library · 2022

The profile is the library's match of the name; two people with one name are not always told apart.

Topics

The most cited first (OpenAlex and our library).

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022 · 456 citations)
Large language models can produce many kinds of harmful content. This Anthropic study examines manual red teaming, in which people deliberately try to provoke bad outputs, as a way both to measure and to reduce such behavior. Crowdworkers held open-ended, multi-turn chats with an AI assistant, tried to steer it…
Scaling Laws and Interpretability of Learning from Repeated Data (2022 · 62 citations)
Large language models often see the same data several times. Sometimes this is done deliberately, to upweight high-quality sources, and sometimes it results from incomplete deduplication. The authors from Anthropic investigate why even a small fraction of repeated data harms models so severely. They train a family of…

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

12 of 16 co-authors with a page, the most papers together first.

Papers of our library cite their works 2,207 times (of the 140,884 papers whose bibliographies we read); 172 citing papers with a page here →.