Fair-PP contributes a synthetic persona-anchored preference dataset for social equity and a reweighted DPO/SFT alignment method that outperforms baselines on LLM-similarity tests.
Safeworld: Geo-diverse safety alignment.Advances in Neural Information Processing Systems, 37:128734– 128768, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Fair-PP contributes a synthetic persona-anchored preference dataset for social equity and a reweighted DPO/SFT alignment method that outperforms baselines on LLM-similarity tests.