mirror of
https://github.com/wassname/moral-maps.git
synced 2026-09-22 13:20:36 +08:00
wassname
bcbdb9cc6f
- 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
87 lines
2.6 KiB
JSON
87 lines
2.6 KiB
JSON
{
|
|
"model": "x-ai/grok-4-fast",
|
|
"foundations": {
|
|
"Care": {
|
|
"n": 132,
|
|
"spearman_r": 0.7345042029622307,
|
|
"spearman_p": 1.2176410154221345e-23,
|
|
"pearson_r": 0.8102300980028216,
|
|
"pearson_p": 5.905981200185428e-32,
|
|
"slope": 17.91275224831169,
|
|
"intercept": -18.86597016699005,
|
|
"mae": 11.767375193181332
|
|
},
|
|
"Fairness": {
|
|
"n": 132,
|
|
"spearman_r": 0.6225605362565393,
|
|
"spearman_p": 1.5959953666830447e-15,
|
|
"pearson_r": 0.8129609595820121,
|
|
"pearson_p": 2.530684016591177e-32,
|
|
"slope": 16.7264766737861,
|
|
"intercept": -19.131907744766767,
|
|
"mae": 11.111987094673093
|
|
},
|
|
"Loyalty": {
|
|
"n": 132,
|
|
"spearman_r": 0.6926099209091109,
|
|
"spearman_p": 3.599007373381228e-20,
|
|
"pearson_r": 0.7484483078065683,
|
|
"pearson_p": 6.0343078480636855e-25,
|
|
"slope": 14.538458435939967,
|
|
"intercept": -15.378022367181732,
|
|
"mae": 9.309441437396758
|
|
},
|
|
"Authority": {
|
|
"n": 132,
|
|
"spearman_r": 0.3856396780981898,
|
|
"spearman_p": 4.961061693936076e-06,
|
|
"pearson_r": 0.6875303659859135,
|
|
"pearson_p": 8.65179834421809e-20,
|
|
"slope": 13.428260762938889,
|
|
"intercept": -13.722907418808013,
|
|
"mae": 11.683327561037107
|
|
},
|
|
"Sanctity": {
|
|
"n": 132,
|
|
"spearman_r": 0.6196021834312778,
|
|
"spearman_p": 2.365393748673303e-15,
|
|
"pearson_r": 0.8887367634786868,
|
|
"pearson_p": 7.21924815710244e-46,
|
|
"slope": 18.316412771225654,
|
|
"intercept": -17.576719463687116,
|
|
"mae": 6.263818224972179
|
|
},
|
|
"Liberty": {
|
|
"n": 132,
|
|
"spearman_r": 0.6020785985113376,
|
|
"spearman_p": 2.2394672471928682e-14,
|
|
"pearson_r": 0.8139335364560988,
|
|
"pearson_p": 1.865088580341189e-32,
|
|
"slope": 14.712894877552804,
|
|
"intercept": -14.163679534840798,
|
|
"mae": 8.163126583084338
|
|
},
|
|
"SocialNorms": {
|
|
"n": 132,
|
|
"spearman_r": -0.4272322719509285,
|
|
"spearman_p": 3.2400850542942107e-07,
|
|
"pearson_r": -0.3207249716209886,
|
|
"pearson_p": 0.00017729490832067168,
|
|
"slope": -9.865750625757574,
|
|
"intercept": 53.56969710715305,
|
|
"mae": 18.84631540933629
|
|
},
|
|
"wrongness": {
|
|
"n": 132,
|
|
"spearman_r": 0.7618659176897857,
|
|
"spearman_p": 2.7640404209932235e-26,
|
|
"pearson_r": 0.8292329749373769,
|
|
"pearson_p": 1.1959738514994125e-34,
|
|
"slope": 0.6992902585652869,
|
|
"intercept": 0.1468375358206399,
|
|
"mae": 0.4377854374641585
|
|
}
|
|
},
|
|
"dominant_accuracy": 0.803030303030303,
|
|
"n_vignettes": 132
|
|
} |