LLMFOSA improves recommendation fairness by using multi-persona LLMs to infer and then remove sensitive attribute information from user embeddings, without using true sensitive labels during training.
Fairness without demographics through knowledge distillation.Advances in Neural Information Processing Systems, 35:19152–19164, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs
LLMFOSA improves recommendation fairness by using multi-persona LLMs to infer and then remove sensitive attribute information from user embeddings, without using true sensitive labels during training.