wassname/Unsupervised-Elicitation
1
0
Fork 0
mirror of https://github.com/wassname/Unsupervised-Elicitation.git synced 2026-08-20 12:10:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

readme: quote the model's own words, intrinsic not implicit, drop dangling 'above'

Browse Source 
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-08-04 13:28:41 +08:00
co-authored by Claudypoo
parent 48c9214d9f
commit 8e394472df
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -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"
```