From ea2ae3b968933dcff289454ffb392aa28822d085 Mon Sep 17 00:00:00 2001
From: "wassname (Michael J Clark)" <1103714+wassname@users.noreply.github.com>
Date: Fri, 10 Apr 2026 10:20:34 +0800
Subject: [PATCH] Update README with reference to related research

Added a reference to related research on multilingual transformers.
---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 007db74..e813308 100644
--- a/README.md
+++ b/README.md
@@ -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.