204 citations · 879 across the 52 of their papers we have counts for
31 papers · 1 filter
Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
Negar Arabzadeh, Andrew Drozdov, Michael Bendersky +1
Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines, enabling the generation of multiple se…
Searching Personal Collections
Michael Bendersky, Donald Metzler, Marc Najork +1
This article describes the history of information retrieval on personal document collections.
Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I
Harrie Oosterhuis, Rolf Jagerman, Zhen Qin +2
The traditional evaluation of information retrieval (IR) systems is generally very costly as it requires manual relevance annotation from human experts. Recent advancements in gene…
Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing
Le Yan, Zhen Qin, Honglei Zhuang +4
The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly askin…
Creator Context for Tweet Recommendation
Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang +6
When discussing a tweet, people usually not only refer to the content it delivers, but also to the person behind the tweet. In other words, grounding the interpretation of the twee…
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…
Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels
Honglei Zhuang, Zhen Qin, Kai Hui +4
Zero-shot text rankers powered by recent LLMs achieve remarkable ranking performance by simply prompting. Existing prompts for pointwise LLM rankers mostly ask the model to choose…
Learning to Rank when Grades Matter
Le Yan, Zhen Qin, Gil Shamir +3
Graded labels are ubiquitous in real-world learning-to-rank applications, especially in human rated relevance data. Traditional learning-to-rank techniques aim to optimize the rank…
Exploring the Viability of Synthetic Query Generation for Relevance Prediction
Aditi Chaudhary, Karthik Raman, Krishna Srinivasan +3
Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models w…
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Zhen Qin, Rolf Jagerman, Kai Hui +9
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researc…
Query Expansion by Prompting Large Language Models
Rolf Jagerman, Honglei Zhuang, Zhen Qin +2
Query expansion is a widely used technique to improve the recall of search systems. In this paper, we propose an approach to query expansion that leverages the generative abilities…
Multivariate Representation Learning for Information Retrieval
Hamed Zamani, Michael Bendersky
Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation…
Metric-agnostic Ranking Optimization
Qingyao Ai, Xuanhui Wang, Michael Bendersky
Ranking is at the core of Information Retrieval. Classic ranking optimization studies often treat ranking as a sorting problem with the assumption that the best performance of rank…
Towards Disentangling Relevance and Bias in Unbiased Learning to Rank
Yunan Zhang, Le Yan, Zhen Qin +5
Unbiased learning to rank (ULTR) studies the problem of mitigating various biases from implicit user feedback data such as clicks, and has been receiving considerable attention rec…
Learning List-Level Domain-Invariant Representations for Ranking
Ruicheng Xian, Honglei Zhuang, Zhen Qin +7
Domain adaptation aims to transfer the knowledge learned on (data-rich) source domains to (low-resource) target domains, and a popular method is invariant representation learning,…
Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
Aijun Bai, Rolf Jagerman, Zhen Qin +6
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score…
RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
Honglei Zhuang, Zhen Qin, Rolf Jagerman +6
Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful s…
Retrieval Augmentation for T5 Re-ranker using External Sources
Kai Hui, Tao Chen, Zhen Qin +4
Retrieval augmentation has shown promising improvements in different tasks. However, whether such augmentation can assist a large language model based re-ranker remains unclear. We…
Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models
Tao Chen, Mingyang Zhang, Jing Lu +2
The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. Howeve…
Improving Neural Ranking via Lossless Knowledge Distillation
Zhen Qin, Le Yan, Yi Tay +4
We explore a novel perspective of knowledge distillation (KD) for learning to rank (LTR), and introduce Self-Distilled neural Rankers (SDR), where student rankers are parameterized…
Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach
Saar Kuzi, Mingyang Zhang, Cheng Li +2
Search engines often follow a two-phase paradigm where in the first stage (the retrieval stage) an initial set of documents is retrieved and in the second stage (the re-ranking sta…
RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble
Michael Bendersky, Honglei Zhuang, Ji Ma +3
In this paper, we report the results of our participation in the TREC-COVID challenge. To meet the challenge of building a search engine for rapidly evolving biomedical collection,…
Interpretable Learning-to-Rank with Generalized Additive Models
Honglei Zhuang, Xuanhui Wang, Michael Bendersky +7
Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating…
Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
Liu Yang, Mingyang Zhang, Cheng Li +2
Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on match…