Hazar Yueksel, Ramon Bertran, et al.
MLSys 2020
Foundation models require fine-tuning to ensure their generative outputs align with intended results for specific tasks. Automating this fine-tuning process is challenging, as it typically needs human feedback that can be expensive to acquire. We present AutoRefine, a method that leverages reinforcement learning for targeted fine-tuning, utilizing direct feedback from measurable performance improvements in specific downstream tasks. We demonstrate the method for a problem arising in algorithmic hiring platforms where linguistic biases influence a recommendation system. In this setting, a generative model seeks to rewrite given job specifications to receive more diverse candidate matches from a recommendation engine which matches jobs to candidates. Our model detects and regulates biases in job descriptions to meet diversity and fairness criteria. The experiments on a public hiring dataset and a real-world hiring platform showcase how large language models can assist in identifying and mitigation biases in the real world.
Hazar Yueksel, Ramon Bertran, et al.
MLSys 2020
Megh Thakkar, Quentin Fournier, et al.
ACL 2024
Natalia Martinez Gil, Dhaval Patel, et al.
UAI 2024
Paulito Palmes, Akihiro Kishimoto, et al.
JuliaCon 2023