New paper proposes conformal fair decoding for LLM-based recommenders
A new arXiv paper introduces conformal fair decoding, a method aimed at large language model recommenders that generate personalized recommendations without task-specific training, addressing fairness when protected attributes change.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-10 05:00 · arXiv cs.AI
Conformal Fair Decoding for Large Language Model Recommenders