mlsanityData to 14 Oct 2026

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

arXiv 2411.16454 ↗First posted 25 Nov 2024cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-solving capabilities for MWPs. Specifically, we rely on the retrieval of problems with similar computational graphs to the given question to serve as exemplars in the prompt, providing the correct reasoning path for the generation model to refer to. Empirical results across six math word problem datasets demonstrate the effectiveness of our proposed method, which achieves a significant improvement of up to 6.7 percent on average in absolute value, compared to baseline methods. These results highlight our method's potential in addressing the reasoning challenges in current LLMs.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

29 of 43 references.

References · 29

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  10. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  11. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 662
  12. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
17 more
  1. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
  2. 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 301
  3. 2024OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Datacited by 200
  4. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  5. 2024Distilling System 2 into System 1cited by 159
  6. 2020Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problemscited by 60
  7. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 53
  8. 2020Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Modelscited by 50
  9. 2023Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preferencecited by 38
  10. 2023Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?cited by 26
  11. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
  12. 2024What Makes Math Word Problems Challenging for LLMs?cited by 19
  13. 2023Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systemscited by 13
  14. 2024Can Large Language Models Reason? A Characterization via 3-SATcited by 12
  15. 2024SuperCLUE-Math6: Graded Multi-Step Math Reasoning Benchmark for LLMs in Chinesecited by 10
  16. 2024CAMBranch: Contrastive Learning with Augmented MILPs for Branchingcited by 10
  17. 2024Panacea: A foundation model for clinical trial search, summarization, design, and recruitmentcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026LLMs with in-context learning for Algorithmic Theoretical Physicscited by 2
  2. 2026Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuningcited by 1
  3. 2026SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematicscited by 1
  4. 2025LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retrievercited by 0
  5. 2026Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matchingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer
  2. 2024Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning
  3. 2022Analogical Math Word Problems Solving with Enhanced Problem-Solution Association
  4. 2024Instructing Large Language Models to Identify and Ignore Irrelevant Conditions
  5. 2025GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
  6. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problems
  7. 2026MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
  8. 2024Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models