mlsanityData to 14 Oct 2026

Neural Module Networks for Reasoning over Text

arXiv 1912.04971 ↗First posted 10 Dec 2019cs.CLcited by 66

Not on the map. Why?

Cited by 21 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable programs composed of learnable modules, performing well on synthetic visual QA domains. However, we find that it is challenging to learn these models for non-synthetic questions on open-domain text, where a model needs to deal with the diversity of natural language and perform a broader range of reasoning. We extend NMNs by: (a) introducing modules that reason over a paragraph of text, performing symbolic reasoning (such as arithmetic, sorting, counting) over numbers and dates in a probabilistic and differentiable manner; and (b) proposing an unsupervised auxiliary loss to help extract arguments associated with the events in text. Additionally, we show that a limited amount of heuristically-obtained question program and intermediate module output supervision provides sufficient inductive bias for accurate learning. Our proposed model significantly outperforms state-of-the-art models on a subset of the DROP dataset that poses a variety of reasoning challenges that are covered by our modules.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 27; 2023: 11; 2024: 6; 2025: 0; 2026: 2.

66 papers.

Sort:

By area:

  1. 2022PAL: Program-aided Language Modelscited by 652
  2. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  3. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  4. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  5. 2022Binding Language Models in Symbolic Languagescited by 228
  6. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  7. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  8. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  9. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
  10. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  11. 2021Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Textcited by 46
  12. 2022Reasoning Like Program Executorscited by 45
38 more
  1. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  2. 2021From LSAT: The Progress and Challenges of Complex Reasoningcited by 43
  3. 2021Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skillscited by 39
  4. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  5. 2022On the Explainability of Natural Language Processing Deep Modelscited by 38
  6. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 35
  7. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  8. 2021Reason first, then respond: Modular Generation for Knowledge-infused Dialoguecited by 32
  9. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  10. 2024RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarioscited by 27
  11. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  12. 2021Factoring Statutory Reasoning as Language Understanding Challengescited by 20
  13. 2021Database Reasoning Over Textcited by 20
  14. 2024Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQAcited by 19
  15. 2022Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Textscited by 18
  16. 2022METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanationcited by 17
  17. 2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoningcited by 16
  18. 2021Teaching Autoregressive Language Models Complex Tasks By Demonstrationcited by 15
  19. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  20. 2023API-Assisted Code Generation for Question Answering on Varied Table Structurescited by 14
  21. 2022UniRPG: Unified Discrete Reasoning over Table and Text as Program Generationcited by 13
  22. 2021VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Taskscited by 11
  23. 2021Truth-Conditional Captioning of Time Series Datacited by 11
  24. 2024Interpretability Needs a New Paradigmcited by 11
  25. 2021Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoningcited by 10
  26. 2021Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalizationcited by 10
  27. 2022DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Datacited by 10
  28. 2022LegoNN: Building Modular Encoder-Decoder Modelscited by 9
  29. 2021Toward Code Generation: A Survey and Lessons from Semantic Parsingcited by 8
  30. 2022AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehensioncited by 8
  31. 2022A Neural-Symbolic Approach to Natural Language Understandingcited by 8
  32. 2022MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generationcited by 7
  33. 2021Paired Examples as Indirect Supervision in Latent Decision Modelscited by 6
  34. 2022Neural Attentive Circuitscited by 6
  35. 2023HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Executioncited by 5
  36. 2023Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perceptioncited by 4
  37. 2024Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thoughtcited by 4
  38. 2022Learning Label Modular Prompts for Text Classification in the Wildcited by 3

50 most cited of 66 All 66 (JSON)