Browse State-of-the-Art › Passage Ranking
Passage Ranking
35 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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.
Syntology 6 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): MS MARCO (6 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| MS MARCO (4 rows) | Fine-tuned SOTA | Text and Code Embeddings by Contrastive Pre-Training | code | — | Compare |
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
1 dataset 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.
Papers archive 2025-07-28
archive papers tagged: 73 · with a code link: 35 · where Syntology ran a sample: 4 (1 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 73 tagged: 1 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 73 of 73, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
18 Aug 2022 3 repositories listedSearch systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores.
-
21 Jun 2021 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, we extract representative feedback embeddings (using KMeans clustering) -- while ensuring that these embeddings…
-
28 Jun 2020 3 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length…
-
27 Jun 2023 2 repositories listedHowever, only learning to generate is insufficient for generative retrieval.
-
31 Aug 2021 2 repositories listedTo test this observation, we employed crowdsourced workers to make preference judgments between the top item returned by a modern neural ranking stack and a judged relevant item.
-
27 Aug 2021 2 repositories listedOur 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…
-
14 Mar 2020 2 repositories listedWe investigate this observation further by varying target words to probe the model's use of latent knowledge.
-
25 Jun 2025 1 repository listedWe propose to unify these tasks using a single ranking foundation model (FM), as it eliminates the need for designing different models for each specific ranking task.
-
19 Dec 2024 1 repository listedFurthermore, we identify two limitations of fine-tuning the full ranking model based on existing methods: (1) sliding window strategy fails to produce a full ranking list as a training label, and (2) the language…
-
9 Dec 2024 1 repository listedGiven the dominance of dense retrievers that do not generalize well beyond their training dataset distributions, domain-specific test sets are essential in evaluating retrieval.
-
24 Jun 2024 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples) · 17 pointer-only (licence)However, few studies have explored how to select appropriate in-context demonstrations for the passage ranking task, which is the focus of this paper.
-
21 Jun 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 4 harvested samples)To address these issues, in this paper, we propose PE-Rank, leveraging the single passage embedding as a good context compression for efficient listwise passage reranking.
-
29 Mar 2024 1 repository listedHowever, Cross-Encoders based on large transformer models (such as BERT or T5) are computationally expensive and allow for scoring only a small number of documents within a reasonably small latency window.
-
24 May 2023 1 repository listedCommon document ranking pipelines in search systems are cascade systems that involve multiple ranking layers to integrate different information step-by-step.
-
19 Apr 2023 1 repository listedIn this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR.
-
7 Apr 2023 1 repository listedT2Ranking comprises more than 300K queries and over 2M unique passages from real-world search engines.
-
10 Dec 2022 1 repository listedKnowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model.
-
26 Sep 2022 1 repository listedFinally, we create a new dataset with questions voiced by human users and use their transcriptions to show that the retrieval performance can further degrade when dealing with natural ASR noise instead of synthetic ASR…
-
14 Sep 2022 1 repository listedIn this study, we propose an imitation adversarial attack on black-box neural passage ranking models.
-
10 Jul 2022 1 repository listedPairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences.
-
21 May 2022 1 repository listedExisting text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high computational cost of pre-trained language models and the large corpus size.
-
4 May 2022 1 repository listedDense retrieval is becoming one of the standard approaches for document and passage ranking.
-
24 Jan 2022 1 repository listedSimilarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20.
-
31 Aug 2021 1 repository listedIn this work, we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 13 languages that was created using machine translation.
-
25 Aug 2021 1 repository listedIn this work, we investigate the use of ANN scores for ranking the candidate documents, in order to decrease the number of candidate documents being fully scored.
-
23 Aug 2021 1 repository listedRecent advances in dense retrieval techniques have offered the promise of being able not just to re-rank documents using contextualised language models such as BERT, but also to use such models to identify documents…
-
14 Jun 2021 1 repository listedRecently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks.
-
13 Oct 2020 1 repository listedThe dependency between an adequate question formulation and correct answer selection is a very intriguing but still underexplored area.
-
6 Oct 2020 1 repository listedBased on this finding, we propose a cross-architecture training procedure with a margin focused loss (Margin-MSE), that adapts knowledge distillation to the varying score output distributions of different BERT and…
-
29 Apr 2020 1 repository listedWe also observe that the performance is additive with the current leading first-stage retrieval methods, further narrowing the gap between inexpensive and cost-prohibitive passage ranking approaches.
-
27 Apr 2020 1 repository listed
-
3 Feb 2020 1 repository listed
-
3 Dec 2019 1 repository listed
-
7 Nov 2019 1 repository listed
-
18 Mar 2019 1 repository listed
-
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems22 May 2025 0 repositories listed
-
Passage Query Methods for Retrieval and Reranking in Conversational Agents28 Feb 2025 0 repositories listed
-
IRLab@iKAT24: Learned Sparse Retrieval with Multi-aspect LLM Query Generation for Conversational Search22 Nov 2024 0 repositories listed
-
RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine8 Oct 2024 0 repositories listed
-
Mamba Retriever: Utilizing Mamba for Effective and Efficient Dense Retrieval15 Aug 2024 0 repositories listed
-
Re-Ranking Step by Step: Investigating Pre-Filtering for Re-Ranking with Large Language Models26 Jun 2024 0 repositories listed
-
Approximate Cluster-Based Sparse Document Retrieval with Segmented Maximum Term Weights13 Apr 2024 0 repositories listed
-
GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation4 Apr 2024 0 repositories listed
-
The Surprising Effectiveness of Rankers Trained on Expanded Queries3 Apr 2024 0 repositories listed
-
Measuring Bias in a Ranked List using Term-based Representations9 Mar 2024 0 repositories listed
-
Searching Dense Representations with Inverted Indexes4 Dec 2023 0 repositories listed
-
PaRaDe: Passage Ranking using Demonstrations with Large Language Models22 Oct 2023 0 repositories listed
-
Context Aware Query Rewriting for Text Rankers using LLM31 Aug 2023 0 repositories listed
-
Vector Search with OpenAI Embeddings: Lucene Is All You Need29 Aug 2023 0 repositories listed
-
Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track23 Aug 2023 0 repositories listed
-
GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking29 May 2023 0 repositories listed
-
How Does Generative Retrieval Scale to Millions of Passages?19 May 2023 0 repositories listed
-
PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN5 Jul 2022 0 repositories listed
-
A Self-supervised Joint Training Framework for Document Reranking1 Jul 2022 0 repositories listed
-
Cross-Lingual Training of Dense Retrievers for Document Retrieval1 Nov 2021 0 repositories listed
-
A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context22 Sep 2021 0 repositories listed
-
Cross-Lingual Training with Dense Retrieval for Document Retrieval3 Sep 2021 0 repositories listed
-
A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques28 Jun 2021 0 repositories listed
-
Contrastive Fine-tuning Improves Robustness for Neural Rankers27 May 2021 0 repositories listed
-
Text-to-Text Multi-view Learning for Passage Re-ranking29 Apr 2021 0 repositories listed
-
Joint Passage Ranking for Diverse Multi-Answer Retrieval17 Apr 2021 0 repositories listed
-
Content-based Models of Quotation1 Apr 2021 0 repositories listed
-
Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering11 Mar 2021 0 repositories listed
-
Improving Passage Re-Ranking with Word N-Gram Aware Coattention Encoder1 Dec 2020 0 repositories listed
-
Making Information Seeking Easier: An Improved Pipeline for Conversational Search1 Nov 2020 0 repositories listed
-
AWS CORD-19 Search: A Neural Search Engine for COVID-19 Literature17 Jul 2020 0 repositories listed
-
Mining Implicit Relevance Feedback from User Behavior for Web Question Answering13 Jun 2020 0 repositories listed
-
Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks8 Jul 2019 0 repositories listed
-
A Passage-Based Approach to Learning to Rank Documents5 Jun 2019 0 repositories listed
-
Passage Ranking with Weak Supervision15 May 2019 0 repositories listed
-
Understanding the Behaviors of BERT in Ranking16 Apr 2019 0 repositories listed
-
A Neural Comprehensive Ranker (NCR) for Open-Domain Question Answering29 Sep 2017 0 repositories listed
-
S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension15 Jun 2017 0 repositories listed
Syntology lines on 4 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections