Lune

EMNLP Findings2025

MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer

Honglin Lin, Zhuoshi Pan, Qizhi Pei, Xin Gao, Yu Li, Mengzhang Cai, Conghui He, Lijun Wu

Abstract

Large Language Models (LLMs) have demonstrated promising capabilities in solving mathematical reasoning tasks, leveraging Chain-of-Thought (CoT) data as a vital component in guiding answer generation. Current paradigms typically generate CoT and answers directly for a given problem, diverging from human problem-solving strategies to some extent. Humans often solve problems by recalling analogous cases and leveraging their solutions to reason about the current task. Inspired by this cognitive process, we propose MetaLadder, a novel framework that explicitly prompts LLMs to recall and reflect on meta-problems, those structurally or semantically analogical problems, alongside their CoT solutions before addressing the target problem. Additionally, we introduce a problem-restating mechanism to enhance the model's comprehension of the target problem by regenerating the original question, which further improves reasoning accuracy. Therefore, the model can achieve reasoning transfer from analogical problems, mimicking human-like "learning from examples" and generalization abilities. Extensive experiments on mathematical benchmarks demonstrate that our MetaLadder significantly boosts LLMs' problem-solving accuracy, largely outperforming standard CoT-based methods (10.3% accuracy gain) and other methods.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • STaR: Bootstrapping Reasoning With Reasoning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Solving Quantitative Reasoning Problems with Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning cites MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
  • Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning cites STaR: Bootstrapping Reasoning With Reasoning
  • Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks cites Generalization through Memorization: Nearest Neighbor Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction FusionQizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li et al.ACL 2025 · 27 citations
  2. REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at OnceZhuoshi Pan, Qizhi Pei, Yu Li, Zinan Tang et al.ACL 2026 · 13 citations
  3. Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model ReasoningHonglin Lin, Qizhi Pei, Zhuoshi Pan, Yu Li et al.NeurIPS 2025 · 12 citations

Builds on19

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  3. Solving Quantitative Reasoning Problems with Language ModelsAitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer et al.NeurIPS 2022 · 2,039 citations
  4. STaR: Bootstrapping Reasoning With ReasoningEric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. GoodmanNeurIPS 2022 · 1,126 citations
  5. Generalization through Memorization: Nearest Neighbor Language ModelsUrvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer et al.ICLR 2020 · 1,038 citations

Related papers

  1. Large Language Models as Analogical ReasonersMichihiro Yasunaga, Xinyun Chen, Yujia Li, Panupong Pasupat et al.ICLR 2024 · 155 citations
  2. Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-ThoughtsTengxiao Liu, Qipeng Guo, Yuqing Yang, Xiangkun Hu et al.EMNLP 2023 · 7 citations
  3. To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningZayne Rea Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang et al.ICLR 2025
  4. The Potential of CoT for Reasoning: A Closer Look at Trace DynamicsGregor Bachmann, Yichen Jiang, Seyed-Mohsen Moosavi-Dezfooli, Moin NabiICLR 2026 · 5 citations
  5. Template-Theorems Graph Construction to Enhance Mathematical Reasoning Capabilities of LLMYarong Lan, Yajing Xu, Huajun ChenAAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines