mlsanityData to 7 Oct 2026

Answering Open-Domain Questions of Varying Reasoning Steps from Text

arXiv 2010.12527 ↗First posted 23 Oct 2020cs.CLcited by 43

Not on the map. Why?

Abstract (arXiv)

We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model to perform all the necessary subtasks -- retrieving supporting facts, reranking them, and predicting the answer from all retrieved documents -- in an iterative fashion. We avoid crucial assumptions of previous work that do not transfer well to real-world settings, including exploiting knowledge of the fixed number of retrieval steps required to answer each question or using structured metadata like knowledge bases or web links that have limited availability. Instead, we design a system that can answer open-domain questions on any text collection without prior knowledge of reasoning complexity. To emulate this setting, we construct a new benchmark, called BeerQA, by combining existing one- and two-step datasets with a new collection of 530 questions that require three Wikipedia pages to answer, unifying Wikipedia corpora versions in the process. We show that our model demonstrates competitive performance on both existing benchmarks and this new benchmark. We make the new benchmark available at https://beerqa.github.io/.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 13; 2023: 7; 2024: 6; 2025: 8; 2026: 5.

43 papers.

Sort:

By area:

  1. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  2. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  3. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  4. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  5. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  6. 2023Natural Language Reasoning, A Surveycited by 61
  7. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
  8. 2025Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Usecited by 45
  9. 2024Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Togethercited by 38
  10. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  11. 2022Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generationcited by 28
  12. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
31 more
  1. 2022Reasoning over Public and Private Data in Retrieval-Based Systemscited by 21
  2. 2022Modeling Multi-hop Question Answering as Single Sequence Predictioncited by 21
  3. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  4. 2022Few-shot Reranking for Multi-hop QA via Language Model Promptingcited by 19
  5. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  6. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14
  7. 2026Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Designcited by 12
  8. 2022Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verificationcited by 11
  9. 2021Iterative Hierarchical Attention for Answering Complex Questions over Long Documentscited by 10
  10. 2025KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracingcited by 8
  11. 2022Zero-Shot Retrieval with Search Agents and Hybrid Environmentscited by 6
  12. 2024HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluationcited by 6
  13. 2026SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answeringcited by 6
  14. 2023Large-Scale Knowledge Synthesis and Complex Information Retrieval from Biomedical Documentscited by 5
  15. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databasescited by 5
  16. 2022ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chainscited by 4
  17. 2025Composing Policy Gradients and Prompt Optimization for Language Model Programscited by 4
  18. 2022Better Retrieval May Not Lead to Better Question Answeringcited by 3
  19. 2022Prompt-based Conservation Learning for Multi-hop Question Answeringcited by 3
  20. 2024RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-trainingcited by 3
  21. 2023Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answeringcited by 2
  22. 2023Teaching Smaller Language Models To Generalise To Unseen Compositional Questionscited by 2
  23. 2026Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Modelscited by 2
  24. 2023Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Databasecited by 1
  25. 2024Momentum Posterior Regularization for Multi-hop Dense Retrievalcited by 1
  26. 2021Tracing Origins: Coreference-aware Machine Reading Comprehensioncited by 0
  27. 2022Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain Question Answeringcited by 0
  28. 2025A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Taskscited by 0
  29. 2025Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answeringcited by 0
  30. 2026Inferential Question Answeringcited by 0
  31. 2026One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAGcited by 0