mlsanityData to 7 Oct 2026

Improving Scientific Document Retrieval with Academic Concept Index

arXiv 2601.00567 ↗First posted 2 Jan 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index, which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation (CCQGen), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts (CCExpand), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 2 Jan 2026.

Builds on

49 of 64 references.

References · 49

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  6. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  7. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  10. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
  11. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  12. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
37 more
  1. 2019Document Expansion by Query Predictioncited by 225
  2. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  3. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  4. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  5. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 154
  6. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  7. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  8. 2022SciRepEval: A Multi-Format Benchmark for Scientific Document Representationscited by 124
  9. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  10. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  11. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  12. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  13. 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
  14. 2017Automated Phrase Mining from Massive Text Corporacited by 70
  15. 2023SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrievalcited by 61
  16. 2021Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedbackcited by 45
  17. 2018A Web-scale system for scientific knowledge explorationcited by 39
  18. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  19. 2021Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similaritycited by 35
  20. 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusterscited by 30
  21. 2020Embedding-based Zero-shot Retrieval through Query Generationcited by 24
  22. 2021OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Servicescited by 20
  23. 2021CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Examplecited by 19
  24. 2023Generative Relevance Feedback with Large Language Modelscited by 19
  25. 2023Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understandingcited by 16
  26. 2024Taxonomy-guided Semantic Indexing for Academic Paper Searchcited by 12
  27. 2023Chain-of-Factors Paper-Reviewer Matchingcited by 11
  28. 2024Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomycited by 11
  29. 2025Syntriever: How to Train Your Retriever with Synthetic Data from LLMscited by 11
  30. 2025Scientific Paper Retrieval with LLM-Guided Semantic-Based Rankingcited by 10
  31. 2023Exploring the Viability of Synthetic Query Generation for Relevance Predictioncited by 9
  32. 2023It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Predictioncited by 9
  33. 2024Synthetic Query Generation using Large Language Models for Virtual Assistantscited by 9
  34. 2025Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generationcited by 6
  35. 2023Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Controlcited by 5
  36. 2023MIReAD: Simple Method for Learning High-quality Representations from Scientific Documentscited by 2
  37. 2025PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrievalcited by 2

Built on by

Not cited yet.