CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

• URL: http://arxiv.org/abs/2502.07316v3
• Date: Mon, 17 Feb 2025 02:51:51 GMT
• Title: CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
• Authors: Junlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu, Junxian He,
• Abstract summary: We propose CodeI/O, a novel approach that condenses diverse reasoning patterns embedded in contextually-grounded codes. By training models to predict inputs/outputs given code and test cases entirely in natural language, we expose them to universal reasoning primitives. Experimental results demonstrate CodeI/O leads to consistent improvements across symbolic, scientific, logic, math & numerical, and commonsense reasoning tasks.
• Score: 47.17755403213469
• License:
• Abstract: Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due to sparse and fragmented training data. To address this issue, we propose CodeI/O, a novel approach that systematically condenses diverse reasoning patterns inherently embedded in contextually-grounded codes, through transforming the original code into a code input-output prediction format. By training models to predict inputs/outputs given code and test cases entirely in natural language as Chain-of-Thought (CoT) rationales, we expose them to universal reasoning primitives -- like logic flow planning, state-space searching, decision tree traversal, and modular decomposition -- while decoupling structured reasoning from code-specific syntax and preserving procedural rigor. Experimental results demonstrate CodeI/O leads to consistent improvements across symbolic, scientific, logic, math & numerical, and commonsense reasoning tasks. By matching the existing ground-truth outputs or re-executing the code with predicted inputs, we can verify each prediction and further enhance the CoTs through multi-turn revision, resulting in CodeI/O++ and achieving higher performance. Our data and models are available at https://github.com/hkust-nlp/CodeIO.

Related papers

• When simplicity meets effectiveness: Detecting code comments coherence with word embeddings and LSTM [6.417777780911223]
  Code comments play a crucial role in software development, as they provide programmers with practical information. Developers tend to leave comments unchanged after updating the code, resulting in a discrepancy between the two artifacts. It is crucial to identify if, given a code snippet, its corresponding comment is coherent and reflects well the intent behind the code.
  arXiv  Detail & Related papers  (2024-05-25T15:21:27Z)
• Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs [57.27982780697922]
  Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process. This paper introduces Lexical Unit Decoding, a novel decoding methodology implemented in a data-driven manner.
  arXiv  Detail & Related papers  (2024-05-24T04:35:13Z)
• Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension [18.919972400933393]
  We propose an advanced pretraining task, "Next Token Prediction+" Following this pretraining, both Code Llama and StarCoder, the prevalent code domain pretraining models, display significant improvements on our logically equivalent code selection task and the code completion task.
  arXiv  Detail & Related papers  (2024-04-13T03:11:07Z)
• Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective [85.48043537327258]
  We propose MANGO (comMents As Natural loGic pivOts), including a comment contrastive training strategy and a corresponding logical comment decoding strategy. Results indicate that MANGO significantly improves the code pass rate based on the strong baselines. The robustness of the logical comment decoding strategy is notably higher than the Chain-of-thoughts prompting.
  arXiv  Detail & Related papers  (2024-04-11T08:30:46Z)
• CodeMind: A Framework to Challenge Large Language Models for Code Reasoning [1.4027589547318842]
  We introduce CodeMind, a framework designed to gauge the code reasoning abilities of Large Language Models (LLMs) CodeMind supports three code reasoning tasks: Independent Execution Reasoning (IER), Dependent Execution Reasoning (DER), and Specification Reasoning (SR)
  arXiv  Detail & Related papers  (2024-02-15T02:24:46Z)
• Code Representation Pre-training with Complements from Program Executions [29.148208436656216]
  We propose FuzzPretrain to explore the dynamic information of programs revealed by their test cases and embed it into the feature representations of code as complements. FuzzyPretrain yielded more than 6%/9% mAP improvements on code search over its counterparts trained with only source code or AST.
  arXiv  Detail & Related papers  (2023-09-04T01:57:22Z)
• When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
  We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
  arXiv  Detail & Related papers  (2023-08-29T17:22:39Z)
• Code Execution with Pre-trained Language Models [88.04688617516827]
  Most pre-trained models for code intelligence ignore the execution trace and only rely on source code and syntactic structures. We develop a mutation-based data augmentation technique to create a large-scale and realistic Python dataset and task for code execution. We then present CodeExecutor, a Transformer model that leverages code execution pre-training and curriculum learning to enhance its semantic comprehension.
  arXiv  Detail & Related papers  (2023-05-08T10:00:05Z)
• Enhancing Semantic Code Search with Multimodal Contrastive Learning and Soft Data Augmentation [50.14232079160476]
  We propose a new approach with multimodal contrastive learning and soft data augmentation for code search. We conduct extensive experiments to evaluate the effectiveness of our approach on a large-scale dataset with six programming languages.
  arXiv  Detail & Related papers  (2022-04-07T08:49:27Z)
• Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding [0.0]
  We present Recursive Decoding, a novel procedure for training and using seq2seq models. Rather than generating an entire output sequence in one pass, models are trained to predict one token at a time. RD yields dramatic improvement on two previously neglected generalization tasks in gSCAN.
  arXiv  Detail & Related papers  (2022-01-27T19:13:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.