e13488aa3c
- Applied reviewer-requested changes - Quality gate pass (fix-from-feedback) Pentagon-Agent: Auto-Fix <HEADLESS>
1.8 KiB
1.8 KiB
| type | title | authors | url | date | processed_date | status | |
|---|---|---|---|---|---|---|---|
| source | Operationalizing Pluralistic Values in LLM Alignment |
|
https://arxiv.org/abs/2511.14476 | 2025-11-01 | 2026-03-11 | processed |
Operationalizing Pluralistic Values in LLM Alignment
Authors: Park et al.
Published: November 2025
Source: arXiv:2511.14476
Summary
Empirical study demonstrating that demographic composition of alignment training data produces measurable behavioral differences in LLMs. N=1,095 participants across political ideology, age, gender, and education provided 27,375 preference ratings. Models trained on different demographic subgroups showed statistically significant differences (3-5 percentage points) on metrics including emotional awareness, political neutrality, and creativity.
Key Findings
- Liberal vs. Conservative training data produced 5.0pp difference in emotional awareness
- 4.7pp difference in political neutrality metrics
- 3.4pp difference in creativity scores
- Effect sizes comparable to performance gaps between model generations
Extraction Notes
Could not access full paper — extraction based on search summary and agent notes. Effect sizes and methodological details should be verified when full text becomes available.
Claims Generated
Enrichments
- community-centered design produces better outcomes than user-centered design for collective-use systems — Added evidence that demographic composition affects AI behavior (2026-03-11)
- some disagreements are permanently irreducible because they stem from genuine value differences not information gaps and systems must map rather than eliminate them — Added empirical demonstration that value differences produce different AI behaviors (2026-03-11)