Causal Localization of Evidence Effects in Transformers
arXiv:2610.36524v1 Announce Type: new Abstract: Can controlled symbolic inputs reveal attention heads that influence a language model's decisions from natural language evidence? We introduce controlled evidence aggregation (CEA), which varies the counts and order of two symbols in otherwise fixed p…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-28 04:00 · arXiv cs.CL
Causal Localization of Evidence Effects in Transformers