SPEX and ProxySPEX Identify Influential LLM Interactions at Scale with Fewer Ablations

Berkeley AI Research introduces SPEX, a signal-processing framework that identifies influential interactions in LLMs using far fewer ablations than exhaustive analysis. A hierarchy-based extension, ProxySPEX, matches SPEX performance with around 10x fewer ablations. The methods apply to feature, data, and model component attribution.