61 citations · 115 across the 19 of their papers we have counts for
23 papers
ReNCE: Learning to Reason by Noise Contrastive Estimation
Wenzheng Zhang, Karl Stratos
GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of outcomes, and promotes those with…
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…
Rethinking Reflection in Pre-Training
Essential AI, :, Darsh J Shah +26
A language model's ability to reflect on its own reasoning provides a key advantage for solving complex problems. While most recent research has focused on how this ability develop…
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…