Navid Rekabsaz

Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors

2023 · arXiv (Cornell University)

Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this problem, we introduce …

Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters

2024 · arXiv (Cornell University)

Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing. Besides optimizing for a modularized debiased model, it is often …