mlsanityData to 7 Oct 2026

The Web as a Knowledge-base for Answering Complex Questions

arXiv 1803.06643 ↗First posted 18 Mar 2018cs.CL cs.AI cs.LGcited by 409

Not on the map. Why?

Cited by 112 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Answering complex questions is a time-consuming activity for humans that requires reasoning and integration of information. Recent work on reading comprehension made headway in answering simple questions, but tackling complex questions is still an ongoing research challenge. Conversely, semantic parsers have been successful at handling compositionality, but only when the information resides in a target knowledge-base. In this paper, we present a novel framework for answering broad and complex questions, assuming answering simple questions is possible using a search engine and a reading comprehension model. We propose to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers. To illustrate the viability of our approach, we create a new dataset of complex questions, ComplexWebQuestions, and present a model that decomposes questions and interacts with the web to compute an answer. We empirically demonstrate that question decomposition improves performance from 20.8 precision@1 to 27.5 precision@1 on this new dataset.

Key facts. Cited by 409 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 57; 2022: 55; 2023: 55; 2024: 62; 2025: 106; 2026: 74.

409 papers.

Sort:

By area:

  1. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  3. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  6. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  7. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  8. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  9. 2023Augmented Language Models: a Surveycited by 398
  10. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  11. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  12. 2022UL2: Unifying Language Learning Paradigmscited by 292
38 more
  1. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  2. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  3. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  4. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  5. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformerscited by 223
  6. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 204
  7. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  8. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  9. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 175
  10. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  11. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  12. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  13. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  14. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  15. 2021WebQA: Multihop and Multimodal QAcited by 109
  16. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 108
  17. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  18. 2023Encyclopedic VQA: Visual questions about detailed properties of fine-grained categoriescited by 105
  19. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  20. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graphcited by 100
  21. 2021Question Answering Over Temporal Knowledge Graphscited by 99
  22. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  23. 2024CRAG -- Comprehensive RAG Benchmarkcited by 94
  24. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  25. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  26. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  27. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 90
  28. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  29. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  30. 2024A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendationscited by 84
  31. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  32. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  33. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
  34. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  35. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  36. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  37. 2022Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answeringcited by 71
  38. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71

50 most cited of 409 All 409 (JSON)