13 citations · 44 across the 11 of their papers we have counts for
11 papers
Unifying Multimodal Retrieval via Document Screenshot Embedding
Xueguang Ma, Sheng-Chieh Lin, Minghan Li +2
In the real world, documents are organized in different formats and varied modalities. Traditional retrieval pipelines require tailored document parsing techniques and content extr…
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
Minghan Li, Xilun Chen, Ari Holtzman +4
Large language models (LLMs) often hallucinate and lack the ability to provide attribution for their generations. Semi-parametric LMs, such as kNN-LM, approach these limitations by…
Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?
Minghan Li, Honglei Zhuang, Kai Hui +5
Query expansion has been widely used to improve the search results of first-stage retrievers, yet its influence on second-stage, cross-encoder rankers remains under-explored. A rec…
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
Sheng-Chieh Lin, Akari Asai, Minghan Li +5
Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however…
Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction
Xinyu Zhang, Minghan Li, Jimmy Lin
Recent progress in information retrieval finds that embedding query and document representation into multi-vector yields a robust bi-encoder retriever on out-of-distribution datase…
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Minghan Li, Sheng-Chieh Lin, Xueguang Ma +1
This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on v…
CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval
Minghan Li, Sheng-Chieh Lin, Barlas Oguz +5
Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. T…
Query Expansion Using Contextual Clue Sampling with Language Models
Linqing Liu, Minghan Li, Jimmy Lin +2
Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models…
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval
Sheng-Chieh Lin, Minghan Li, Jimmy Lin
Pre-trained language models have been successful in many knowledge-intensive NLP tasks. However, recent work has shown that models such as BERT are not ``structurally ready'' to ag…
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking
Minghan Li, Xinyu Zhang, Ji Xin +2
In information retrieval (IR), candidate set pruning has been commonly used to speed up two-stage relevance ranking. However, such an approach lacks accurate error control and ofte…
Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering
Minghan Li, Jimmy Lin
One key feature of dense passage retrievers (DPR) is the use of separate question and passage encoder in a bi-encoder design. Previous work on generalization of DPR mainly focus on…