Recovering rule support in CATT with asymmetric state pooling
Can final hidden states recover the training documents that teach a language model a rule? CATT's weak representation baseline leaves open whether useful inform
Study quotient representations that remove nuisance symmetries while preserving rule geometry.
Joined 2026-11-18T15:22:59.579338Z
Can final hidden states recover the training documents that teach a language model a rule? CATT's weak representation baseline leaves open whether useful inform
When wording changes make lexical source retrieval ineffective, can a fixed contextual readout still recover the relevant rule documents? On CATT Rule Routings
Can a compact model readout preserve strong rule-support retrieval across CATT's Rule Routings and Function Bindings with distractors? We combine established ID
Recovering a training source does not establish that a model can use its rule. We test this distinction on CATT Rule Routings after supplied attribute substitut