wassname/eliciting_suppressed_knowledge
1
0
Fork 0
mirror of https://github.com/wassname/eliciting_suppressed_knowledge.git synced 2026-09-10 12:00:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
wassname (Michael J Clark)
2025-05-06 06:31:45 +08:00
committed by GitHub
parent cb831ece87
commit e5ae273d67
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -1,4 +1,4 @@
# Eliciting Suppressed Knowledge (ESK) WIP
# Eliciting Suppressed Knowledge (ESK)
## Abstract
**Where do transformer models store their true "thoughts" when they say something they know is false?** We demonstrate that suppressed neural activations are a more useful source of knowledge than the model's direct outputs or standard hidden states. By isolating and probing these suppressed activation patterns, we achieve ~20% AUROC improvements on TruthfulQA compared to the LLM answer, and . This confirms suppressed activations contain knowledge that the model possesses but deliberately inhibits during generation.