# Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering Source: [Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:23:26.146Z Authors: Hao Cheng, Hao Fang, Xiaodong Liu, Jianfeng Gao Published: 2022-10-11T05:33:25.000Z ## Abstract Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular. Specifically, the de-facto architecture for open-domain question answering uses two isomorphic encoders that are initialized from the same pretrained model but separately parameterized for questions and passages. This bi-encoder architecture is parameter-inefficient in that there is no parameter sharing between encoders. Further, recent studies show that such dense retrievers underperform BM25 in various settings. We thus propose a new architecture, Task-aware Specialization for dense Retrieval (TASER), which enables parameter sharing by interleaving shared and specialized blocks in a single encoder. Our experiments on five question answering datasets show that TASER can achieve superior accuracy, surpassing BM25, while using about 60% of the parameters as bi-encoder dense retrievers. In out-of-domain evaluations, TASER is also empirically more robust than bi-encoder dense retrievers. Our code is available at https://github.com/microsoft/taser. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()