From 8e394472dfe68999e1e0e8e8e9a1c886f46b1144 Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Tue, 4 Aug 2026 13:28:41 +0800
Subject: [PATCH] readme: quote the model's own words, intrinsic not implicit,
 drop dangling 'above'

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
---
 README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 5318c86..fd6106e 100644
--- a/README.md
+++ b/README.md
@@ -9,13 +9,13 @@ It thought the TruthfulQA v2 classes were
 - **Set A - "Factually-correct/Scientifically-supported/Nuanced or context-dependent statement"**
 - **Set B - "Myth/Misconception/False-or-over-simplified claim"**
 
-So factual fits with the dataset, as does supported. But nuanced vs simplified is a confound, and differs from the intention of the dataset, which is closer to "2020 era misconceptions" in my mind.
+So "factually-correct" fits with the dataset, as does "scientifically-supported". But "nuanced" vs "over-simplified" is a confound, and differs from the intention of the dataset, which is closer to "2020 era misconceptions" in my mind.
 
 ## What is this?
 
-This is a simplified fork of [unsupervised-elicitation](https://github.com/Jiaxin-Wen/Unsupervised-Elicitation) ([Wen et al. 2025](https://arxiv.org/abs/2506.10139)) which is a paper that uses in-context metalearning, requiring it to be consistent and mutually predictive. We are using two things here
+This is a simplified fork of [unsupervised-elicitation](https://github.com/Jiaxin-Wen/Unsupervised-Elicitation) ([Wen et al. 2025](https://arxiv.org/abs/2506.10139)) which is a paper that uses in-context metalearning, requiring it to be consistent and mutually predictive. We are using two kinds of signal here
 
-Implicit:
+Intrinsic:
 - in-context metalearning e.g. "given these examples complete the pattern"
 
 Extrinsic:
@@ -70,7 +70,7 @@ uv run src/simple_icm.py
 ## How does an LLM explain its unsupervised labelling of the DailyDilemmas moral dataset?
 
 ```
-By roughly the middle of the log it converged on the cleaner dichotomy above:
+By roughly the middle of the log it converged on this dichotomy:
   - A = "restraint / self-care / principle-keeping"
   - B = "assertive / duty-bound / risk-taking for a moral end"
 ```