wassname/eliciting_suppressed_knowledge
1
0
Fork 0
mirror of https://github.com/wassname/eliciting_suppressed_knowledge.git synced 2026-09-09 11:21:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README with reference to related research

Browse Source 
Added a reference to related research on multilingual transformers.
This commit is contained in:
wassname (Michael J Clark)
2026-04-10 10:20:34 +08:00
committed by GitHub
parent e5ae273d67
commit ea2ae3b968
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2
View File
@@ -36,6 +36,8 @@ Our approach connects directly to two emerging lines of research:
Where previous work focused on architectural components (identifying suppression neurons) or documenting the unfaithfulness phenomenon, our research bridges these streams by showing we can extract more accurate information from the very activations being suppressed.
See also [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://arxiv.org/abs/2402.10588)
## Hypothesis
Suppressed neural activations contain more accurate information than what appears in model outputs. A linear probe of these suppressed activations should therefore outperform both direct model outputs and probes of standard hidden states on truthfulness tasks.