ACL Findings2024
Referral Augmentation for Zero-Shot Information Retrieval
Michael Tang, Shunyu Yao, John Yang, Karthik Narasimhan
Abstract
We propose Referral-Augmented Retrieval (RAR), a simple technique that concatenates document indices with referrals: text from other documents that cite or link to the given document. We find that RAR provides significant performance gains for tasks across paper retrieval, entity retrieval, and open-domain question-answering in both zero-shot and indomain (e.g., fine-tuned) settings. We examine how RAR provides especially strong improvements on more structured tasks, and can greatly outperform generative text expansion techniques such as DocT5Query (Nogueira et al., 2019) and Query2Doc (Wang et al., 2023), with a 37% and 21% absolute improvement on ACL paper retrieval, respectively. We also compare three ways to aggregate referrals for RAR. Overall, we believe RAR can help revive and re-contextualize the classic information retrieval idea of using anchor texts to improve the representations of documents in a wide variety of corpuses in the age of neural retrieval. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Precise Zero-Shot Dense Retrieval without Relevance Labels cites SimCSE: Simple Contrastive Learning of Sentence Embeddings
- LitSearch: A Retrieval Benchmark for Scientific Literature Search cites S2ORC: The Semantic Scholar Open Research Corpus
- LitSearch: A Retrieval Benchmark for Scientific Literature Search cites SimCSE: Simple Contrastive Learning of Sentence Embeddings
Cited by top-tier papers1
Builds on9
- Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
- SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
- S2ORC: The Semantic Scholar Open Research CorpusKyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney et al.ACL 2020 · 424 citations
- Distilling Knowledge from Reader to Retriever for Question AnsweringGautier Izacard, Edouard GraveICLR 2021 · 317 citations
- Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
Related papers
- Generation-Augmented Retrieval for Open-Domain Question AnsweringYuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen et al.ACL 2021
- Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question AnsweringYung-Sung Chuang, Wei Fang, Shang-Wen Li, Wen-tau Yih et al.ACL Findings 2023 · 19 citations
- Improving Passage Retrieval with Zero-Shot Question GenerationDevendra Singh Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan et al.EMNLP 2022 · 69 citations
- BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex DocumentsShu Wang, Yingli Zhou, Yixiang FangVLDB 2026 · 16 citations
- Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented GenerationShicheng Xu, Liang Pang, Mo Yu, Fandong Meng et al.ACL 2024
