Staging: a test copy of Stemma. Its data is wiped often and nothing here is paid for.

Stemma.

Fields

Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.

Subfield

Alignment and safety evaluations

Benchmarks: HarmBench, JailbreakBench, StrongREJECT, XSTest and others. Datasets: AdvBench, JBB-Behaviors, TruthfulQA, BBQ and others. Baselines: GCG, PAIR, TAP, AutoDAN and others.

No papers here yet