# Adaptive Re-Ranking with a Corpus Graph

arXiv: https://arxiv.org/abs/2208.08942 · HTML: https://mlsanity.com/paper/2208.08942/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2022.

## Built on by (most cited first, 23 of 23)

- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [Ranked List Truncation for Large Language Model-based Re-Ranking](https://mlsanity.com/paper/2404.18185/) (2024)
- [Guiding Retrieval using LLM-based Listwise Rankers](https://mlsanity.com/paper/2501.09186/) (2025)
- [Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy](https://mlsanity.com/paper/2403.04160/) (2024)
- [Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking](https://mlsanity.com/paper/2505.21815/) (2025)
- [Lexically-Accelerated Dense Retrieval](https://mlsanity.com/paper/2307.16779/) (2023)
- [Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval](https://mlsanity.com/paper/2509.07163/) (2025)
- [Shallow Cross-Encoders for Low-Latency Retrieval](https://mlsanity.com/paper/2403.20222/) (2024)
- [LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval](https://mlsanity.com/paper/2510.13217/) (2025)
- [Test-time Corpus Feedback: From Retrieval to RAG](https://mlsanity.com/paper/2508.15437/) (2025)
- [Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization](https://mlsanity.com/paper/2302.01148/) (2023)
- [Query-Specific Knowledge Graphs for Complex Finance Topics](https://mlsanity.com/paper/2211.04142/) (2022)
- [Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders](https://mlsanity.com/paper/2405.03651/) (2024)
- [Predicting from a Different Perspective: A Re-ranking Model for Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2405.16902/) (2024)
- [Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets](https://mlsanity.com/paper/2509.24815/) (2025)
- [SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization](https://mlsanity.com/paper/2512.16956/) (2025)
- [R3-SQL: Ranking Reward and Resampling for Text-to-SQL](https://mlsanity.com/paper/2604.25325/) (2026)
- [Online Distillation for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2306.09657/) (2023)
- [GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs](https://mlsanity.com/paper/2601.18579/) (2026)
- [PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID](https://mlsanity.com/paper/2607.18626/) (2026)
- [Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis](https://mlsanity.com/paper/2608.30525/) (2026)
- [ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap](https://mlsanity.com/paper/2609.26237/) (2026)
- [BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval](https://mlsanity.com/paper/2609.27213/) (2026)

## Abstract (arXiv)

Search systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores. The process enables the use of highly-effective but expensive scoring functions that are not suitable for use directly in structures like inverted indices or approximate nearest neighbour indices. However, re-ranking pipelines are inherently limited by the recall of the initial candidate pool; documents that are not identified as candidates for re-ranking by the initial retrieval function cannot be identified. We propose a novel approach for overcoming the recall limitation based on the well-established clustering hypothesis. Throughout the re-ranking process, our approach adds documents to the pool that are most similar to the highest-scoring documents up to that point. This feedback process adapts the pool of candidates to those that may also yield high ranking scores, even if they were not present in the initial pool. It can also increase the score of documents that appear deeper in the pool that would have otherwise been skipped due to a limited re-ranking budget. We find that our Graph-based Adaptive Re-ranking (GAR) approach significantly improves the performance of re-ranking pipelines in terms of precision- and recall-oriented measures, is complementary to a variety of existing techniques (e.g., dense retrieval), is robust to its hyperparameters, and contributes minimally to computational and storage costs. For instance, on the MS MARCO passage ranking dataset, GAR can improve the nDCG of a BM25 candidate pool by up to 8% when applying a monoT5 ranker.