wassname/moral-maps
1
0
Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-09-06 16:50:34 +08:00
Code Issues Packages Projects Releases Wiki Activity
65 Commits 8 Branches 0 Tags
verbose-debug-level
Commit Graph
6 Commits
Author SHA1 Message Date
wassname b20ec56a09 forced-choice unification: drop legacy llm_/calibrated_, normalize human_*, justfile->09 2026-05-08 16:02:25 +08:00
wassname 0442935279 clean 2026-05-08 15:33:29 +08:00
wassname b12770cb78 fixes, naming 2026-05-08 15:23:54 +08:00
wassname c96d02a675 refactor 2026-05-08 15:15:14 +08:00
wassname d796df85c8 improved to have better airisk, better eval that distinguished factors 2026-05-08 14:04:56 +08:00
wassname bcbdb9cc6f feat: multi-label moral foundation ratings with z-scored frame averaging and human calibration 
- Add scripts/07_multilabel.py: LLM judge rates all 7 foundations per vignette
  using violation (forward) and acceptability (reverse) frames
- Foundation definitions drawn from Clifford et al. (2015) survey rubric
- Z-score each frame per foundation before averaging to cancel range bias
- Calibrate LLM Likert → human % via per-foundation OLS (classic set only)
- Add scripts/07a_merge_labels.py: merges llm_* and calibrated_* into vignette files
- Update README and HF dataset card with methodology and calibration quality table
- Classic set: 80.3% dominant-foundation accuracy, Pearson r 0.69-0.89 per foundation
 2026-05-03 12:48:14 +08:00