mlsanityData to 14 Oct 2026

textttMixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity

arXiv 2407.10691 ↗First posted 15 Jul 2024cs.IR cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Recent studies show the growing significance of document retrieval in the generation of LLMs, i.e., RAG, within the scientific domain by bridging their knowledge gap. However, dense retrievers often struggle with domain-specific retrieval and complex query-document relationships, particularly when query segments correspond to various parts of a document. To alleviate such prevalent challenges, this paper introduces textttMixGR, which improves dense retrievers' awareness of query-document matching across various levels of granularity in queries and documents using a zero-shot approach. textttMixGR fuses various metrics based on these granularities to a united score that reflects a comprehensive query-document similarity. Our experiments demonstrate that textttMixGR outperforms previous document retrieval by 24.7%, 9.8%, and 6.9% on nDCG@5 with unsupervised, supervised, and LLM-based retrievers, respectively, averaged on queries containing multiple subqueries from five scientific retrieval datasets. Moreover, the efficacy of two downstream scientific question-answering tasks highlights the advantage of textttMixGR to boost the application of LLMs in the scientific domain. The code and experimental datasets are available.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 45 of its 73 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

45 of 73 references.

References · 45

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  11. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  12. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
33 more
  1. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  3. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  4. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  8. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  9. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  10. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  11. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  12. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  13. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  14. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  15. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  16. 2019Multilingual Universal Sentence Encoder for Semantic Retrievalcited by 193
  17. 2020Pre-training Tasks for Embedding-based Large-scale Retrievalcited by 153
  18. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  19. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118
  20. 2021TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learningcited by 116
  21. 2021Decontextualization: Making Sentences Stand-Alonecited by 102
  22. 2020Learning Dense Representations of Phrases at Scalecited by 91
  23. 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
  24. 2021Domain-matched Pre-training Tasks for Dense Retrievalcited by 53
  25. 2021A Replication Study of Dense Passage Retrievercited by 37
  26. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  27. 2021ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answerscited by 29
  28. 2021Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representationscited by 27
  29. 2022Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Modelscited by 26
  30. 2019A Summarization System for Scientific Documentscited by 17
  31. 2023Constructing Tree-based Index for Efficient and Effective Dense Retrievalcited by 15
  32. 2022MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrievalcited by 10
  33. 2020A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolutioncited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 8.

9 papers.

  1. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 42
  2. 2024OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Modelscited by 23
  3. 2025cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Treecited by 17
  4. 2025Scientific Paper Retrieval with LLM-Guided Semantic-Based Rankingcited by 10
  5. 2025MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrieverscited by 7
  6. 2025CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrievalcited by 6
  7. 2025LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generationcited by 5
  8. 2025Revela: Dense Retriever Learning via Language Modelingcited by 3
  9. 2025Causal Retrieval with Semantic Considerationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation
  2. 2024Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG
  3. 2025Mixture-of-RAG: Integrating Text and Tables with Large Language Models
  4. 2026When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
  5. 2025Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking
  6. 2026SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
  7. 2023BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval
  8. 2026Uncertainty-Aware Hybrid Retrieval for Long-Document RAG