24 citations · 25 across the 6 of their papers we have counts for
5 papers · 1 filter
ImpRAG: Retrieval-Augmented Generation with Implicit Queries
Wenzheng Zhang, Xi Victoria Lin, Karl Stratos +2
Retrieval-Augmented Generation (RAG) systems traditionally treat retrieval and generation as separate processes, requiring explicit textual queries to connect them. This separation…
Seq2seq is All You Need for Coreference Resolution
Wenzheng Zhang, Sam Wiseman, Karl Stratos
Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that…
Improving Multitask Retrieval by Promoting Task Specialization
Wenzheng Zhang, Chenyan Xiong, Karl Stratos +1
In multitask retrieval, a single retriever is trained to retrieve relevant contexts for multiple tasks. Despite its practical appeal, naive multitask retrieval lags behind task-spe…
EntQA: Entity Linking as Question Answering
Wenzheng Zhang, Wenyue Hua, Karl Stratos
A conventional approach to entity linking is to first find mentions in a given document and then infer their underlying entities in the knowledge base. A well-known limitation of t…
Understanding Hard Negatives in Noise Contrastive Estimation
Wenzheng Zhang, Karl Stratos
The choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives -- highest-scoring incorrect examples under the model -- are eff…