Passage Retrieval

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

19 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 19 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

10 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 133 papers with code (268 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Dense Passage Retrieval for Open-Domain Question Answering
  10 Apr 2020 19 repositories listed Syntology ran 10 of 14 samples · 4 unverified · 9 pointer-only (licence)
  Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method.
• Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
  2 Jul 2020 8 repositories listed
  Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge.
• Unsupervised Dense Information Retrieval with Contrastive Learning
  16 Dec 2021 6 repositories listed Syntology ran 1 of 5 samples · 4 unverified
  In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various retrieval settings.
• Passage Re-ranking with BERT
  13 Jan 2019 6 repositories listed Syntology ran 2 of 13 samples · 11 unverified
  Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural…
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
  1 Jul 2020 5 repositories listed Syntology ran 3 of 12 samples · 9 unverified
  In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing.
• BM25S: Orders of magnitude faster lexical search via eager sparse scoring
  4 Jul 2024 3 repositories listed Syntology ran 10 of 22 samples · 12 unverified
  We introduce BM25S, an efficient Python-based implementation of BM25 that only depends on Numpy and Scipy.
• Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval
  20 Jan 2024 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  In this study, we aim to shed light on this issue by revealing that masked auto-encoder (MAE) pre-training with enhanced decoding significantly improves the term coverage of input tokens in dense representations,…
• DAPR: A Benchmark on Document-Aware Passage Retrieval
  23 May 2023 3 repositories listed
  This drives us to build a benchmark for this task including multiple datasets from heterogeneous domains.
• ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System
  30 May 2022 3 repositories listed
  This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA).
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
  2 Dec 2021 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks.
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
  17 Apr 2021 3 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval.
• Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training
  15 Nov 2023 2 repositories listed Syntology ran 15 of 17 samples · 2 unverified
  While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts.
• Fine-Tuning LLaMA for Multi-Stage Text Retrieval
  12 Oct 2023 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified
  Our findings demonstrate that the effectiveness of large language models indeed surpasses that of smaller models.
• MiniLLM: Knowledge Distillation of Large Language Models
  14 Jun 2023 2 repositories listed
  In this work, we propose a KD approach that distills LLMs into smaller language models.
• I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
  4 Jun 2023 2 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  Moreover, the proposed implicit interaction is compatible with special pre-training and knowledge distillation for passage retrieval, which brings a new state-of-the-art performance.
• Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering
  26 May 2023 2 repositories listed
  We propose EAR, a query Expansion And Reranking approach for improving passage retrieval, with the application to open-domain question answering.
• Query-as-context Pre-training for Dense Passage Retrieval
  19 Dec 2022 2 repositories listed
  Recently, methods have been developed to improve the performance of dense passage retrieval by using context-supervised pre-training.
• DPTDR: Deep Prompt Tuning for Dense Passage Retrieval
  24 Aug 2022 2 repositories listed
  We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources.
• ConTextual Masked Auto-Encoder for Dense Passage Retrieval
  16 Aug 2022 2 repositories listed
  Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i.
• QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs
  25 May 2022 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Our results highlight the need for developing ODQA models that handle a broad range of question types, including single and multi-answer questions.
• DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
  19 Mar 2022 2 repositories listed
  In this paper, we present DuReader_retrieval, a large-scale Chinese dataset for passage retrieval.
• Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
  7 Mar 2022 2 repositories listed
  We find that the performance of retrieval models trained on dataset from general domain will inevitably decrease on specific domain.
• Large Dual Encoders Are Generalizable Retrievers
  15 Dec 2021 2 repositories listed
  With multi-stage training, surprisingly, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization.
• Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
  13 Oct 2021 2 repositories listed
  Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to…
• Slot Filling for Biomedical Information Extraction
  17 Sep 2021 2 repositories listed
  In this work we present a slot filling approach to the task of biomedical IE, effectively replacing the need for entity and relation-specific training data, allowing us to deal with zero-shot settings.
• Robust Retrieval Augmented Generation for Zero-shot Slot Filling
  31 Aug 2021 2 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI.
• Dealing with Typos for BERT-based Passage Retrieval and Ranking
  27 Aug 2021 2 repositories listed
  Our experimental results on the MS MARCO passage ranking dataset show that, with our proposed typos-aware training, DR and BERT re-ranker can become robust to typos in queries, resulting in significantly improved…
• Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently
  20 Oct 2020 2 repositories listed
  Through this process, it teaches the DR model how to retrieve relevant documents from the entire corpus instead of how to rerank a potentially biased sample of documents.
• Open-Domain Question Answering Goes Conversational via Question Rewriting
  10 Oct 2020 2 repositories listed Syntology ran 0 of 8 samples · 8 unverified
  We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs.
• Overview of the TREC 2019 deep learning track
  17 Mar 2020 2 repositories listed
  The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime.

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.