claim
active
claim:this-setting-multi-token-autoregressive-generation-on-natural-red-team-prompts-is-closer-to-realistic-safety-evaluations-than-wu-hilton-s

This setting (multi-token autoregressive generation on natural red-team prompts) is closer to realistic safety evaluations than Wu & Hilton's

Positions the work.

Source paper

extracted_from
Predicting Rare LLM Failures with 30× Fewer Rollouts
Santiago Aranguri

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.