mlsanityData to 14 Oct 2026

Better Retrieval May Not Lead to Better Question Answering

arXiv 2205.03685 ↗First posted 7 May 2022cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC). A popular approach to improve the system's performance is to improve the quality of the retrieved context from the IR stage. In this work we show that for StrategyQA, a challenging open-domain QA dataset that requires multi-hop reasoning, this common approach is surprisingly ineffective -- improving the quality of the retrieved context hardly improves the system's performance. We further analyze the system's behavior to identify potential reasons.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 7 May 2022.

Builds on

18 of 24 references.

References · 18

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  5. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  8. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
  9. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  10. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 162
  11. 2019Compositional Questions Do Not Necessitate Multi-hop Reasoningcited by 88
  12. 2019Dynamically Fused Graph Network for Multi-hop Reasoningcited by 63
6 more
  1. 2019Revealing the Importance of Semantic Retrieval for Machine Reading at Scalecited by 50
  2. 2020Answering Open-Domain Questions of Varying Reasoning Steps from Textcited by 43
  3. 2019Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoningcited by 28
  4. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  5. 2020A Simple Yet Strong Pipeline for HotpotQAcited by 24
  6. 2016This before That: Causal Precedence in the Biomedical Domaincited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.

3 papers.

  1. 2023Teaching Smaller Language Models To Generalise To Unseen Compositional Questionscited by 2
  2. 2024Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)cited by 0
  3. 2026Gradually Excavating External Knowledge for Implicit Complex Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Diagnosing the Fact-Grounding Gap in Multi-Hop Question Answering
  2. 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
  3. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
  4. 2025PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
  5. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
  6. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
  7. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
  8. 2024Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization