mlsanityData to 7 Oct 2026

Generate & Rank: A Multi-task Framework for Math Word Problems

arXiv 2109.03034 ↗First posted 7 Sep 2021cs.CL cs.AIcited by 82

Not on the map. Why?

Cited by 33 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Math word problem (MWP) is a challenging and critical task in natural language processing. Many recent studies formalize MWP as a generation task and have adopted sequence-to-sequence models to transform problem descriptions to mathematical expressions. However, mathematical expressions are prone to minor mistakes while the generation objective does not explicitly handle such mistakes. To address this limitation, we devise a new ranking task for MWP and propose Generate & Rank, a multi-task framework based on a generative pre-trained language model. By joint training with generation and ranking, the model learns from its own mistakes and is able to distinguish between correct and incorrect expressions. Meanwhile, we perform tree-based disturbance specially designed for MWP and an online update to boost the ranker. We demonstrate the effectiveness of our proposed method on the benchmark and the results show that our method consistently outperforms baselines in all datasets. Particularly, in the classical Math23k, our method is 7% (78.4% rightarrow 85.4%) higher than the state-of-the-art.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 7 Sep 2021.

Builds on

16 of 37 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  8. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  9. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  10. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  11. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  12. 2021Unified Pre-training for Program Understanding and Generationcited by 361
4 more
  1. 2016Solving General Arithmetic Word Problemscited by 353
  2. 2018Translating a Math Word Problem to an Expression Treecited by 57
  3. 2018Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problemscited by 49
  4. 2016Unit Dependency Graph and its Application to Arithmetic Word Problem Solvingcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 28; 2023: 29; 2024: 10; 2025: 10; 2026: 3.

82 papers.

Sort:

By area:

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Let's Verify Step by Stepcited by 3,598
  5. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  6. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  7. 2022CodeT: Code Generation with Generated Testscited by 369
  8. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  9. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  10. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  11. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  12. 2023Universal Self-Consistency for Large Language Model Generationcited by 198
38 more
  1. 2023Talk like a Graph: Encoding Graphs for Large Language Modelscited by 175
  2. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  3. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  4. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  5. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  6. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  7. 2023OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoningcited by 84
  8. 2023Language Model Self-improvement by Reinforcement Learning Contemplationcited by 75
  9. 2022A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Modelscited by 68
  10. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  11. 2024Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learningcited by 63
  12. 2023Guiding Language Model Reasoning with Planning Tokenscited by 58
  13. 2023FIMO: A Challenge Formal Dataset for Automated Theorem Provingcited by 54
  14. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  15. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 42
  16. 2023The Consensus Game: Language Model Generation via Equilibrium Searchcited by 35
  17. 2022Fault-Aware Neural Code Rankerscited by 33
  18. 2023Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generationcited by 27
  19. 2025BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanismcited by 25
  20. 2023TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Modelscited by 24
  21. 2023Mathematical Language Models: A Surveycited by 24
  22. 2022Generating Executable Action Plans with Environmentally-Aware Language Modelscited by 21
  23. 2024Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlocited by 21
  24. 2023A Symbolic Character-Aware Model for Solving Geometry Problemscited by 20
  25. 2023Interpretable Math Word Problem Solution Generation Via Step-by-step Planningcited by 17
  26. 2022Chaining Simultaneous Thoughts for Numerical Reasoningcited by 14
  27. 2022Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problemcited by 13
  28. 2023Asking Before Acting: Gather Information in Embodied Decision Making with Language Modelscited by 12
  29. 2023Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoningcited by 12
  30. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Modelscited by 12
  31. 2022LogiGAN: Learning Logical Reasoning via Adversarial Pre-trainingcited by 11
  32. 2023CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verificationcited by 11
  33. 2025When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifierscited by 11
  34. 2022Self-consistent Reasoning For Solving Math Word Problemscited by 10
  35. 2022DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Datacited by 10
  36. 2023JarviX: A LLM No code Platform for Tabular Data Analysis and Optimizationcited by 10
  37. 2022Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solverscited by 9
  38. 2023Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problemscited by 9

50 most cited of 82 All 82 (JSON)