mlsanityData to 14 Oct 2026

Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences

arXiv 2503.13109 ↗First posted 17 Mar 2025cs.CLcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive reasoning, is not well studied. We attribute the reason to the fact that obtaining high-quality process supervision data is challenging for inductive reasoning. Towards this end, we novelly employ number sequences as the source of inductive reasoning data. We package sequences into algorithmic problems to find the general term of each sequence through a code solution. In this way, we can verify whether the code solution holds for any term in the current sequence, and inject case-based supervision signals by using code unit tests. We build a sequence synthetic data pipeline and form a training dataset CodeSeq. Experimental results show that the models tuned with CodeSeq improve on both code and comprehensive reasoning benchmarks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 28 of its 42 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

28 of 42 references.

References · 28

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  8. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  9. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  10. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  11. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 284
  12. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 238
16 more
  1. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  2. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 186
  3. 2023Large Language Models for Generative Information Extraction: A Surveycited by 185
  4. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
  5. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 156
  6. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  7. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  8. 2024Comprehensive Exploration of Synthetic Data Generation: A Surveycited by 60
  9. 2023On the Impact of Calibration Data in Post-training Quantization and Pruningcited by 58
  10. 2024MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Codecited by 39
  11. 2023Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Modelscited by 27
  12. 2024TasTe: Teaching Large Language Models to Translate through Self-Reflectioncited by 27
  13. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  14. 2024INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuningcited by 20
  15. 2024CLAP: Learning Transferable Binary Code Representations with Natural Language Supervisioncited by 17
  16. 2024Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributescited by 7

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025A Survey of Inductive Reasoning for Large Language Modelscited by 8

Similar, not cited

Close in wording, no citation either way

  1. 2025Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
  2. 2023Hypothesis Search: Inductive Reasoning with Language Models
  3. 2025InductionBench: LLMs Fail in the Simplest Complexity Class
  4. 2024Benchmarking Large Language Models with Integer Sequence Generation Tasks
  5. 2024The Role of Deductive and Inductive Reasoning in Large Language Models
  6. 2026ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
  7. 2025On LLM-Based Scientific Inductive Reasoning Beyond Equations
  8. 2023Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement