VISUALCODER: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2410.23402v1
• Date: Wed, 30 Oct 2024 19:07:01 GMT
• Title: VISUALCODER: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
• Authors: Cuong Chi Le, Hoang-Chau Truong-Vinh, Huy Nhat Phan, Dung Duy Le, Tien N. Nguyen, Nghi D. Q. Bui,
• Abstract summary: We introduce Visual Coder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with a visual Control Flow Graph (CFG) By aligning code snippets with their corresponding CFGs, Visual Coder provides deeper insights into execution flow, enabling more accurate predictions of code behavior. Our experiments demonstrate that augmenting LLMs with visual CFGs significantly outperforms text-based CFG descriptions in code reasoning tasks.
• Score: 10.70881967278009
• License:
• Abstract: Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce Visual Coder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with a visual Control Flow Graph (CFG). By aligning code snippets with their corresponding CFGs, Visual Coder provides deeper insights into execution flow, enabling more accurate predictions of code behavior. Our experiments demonstrate that augmenting LLMs with visual CFGs significantly outperforms text-based CFG descriptions in code reasoning tasks. We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation.

Related papers

• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Learning to Predict Program Execution by Modeling Dynamic Dependency on Code Graphs [11.347234752942684]
  This paper introduces a novel machine learning-based framework called CodeFlow to predict code coverage and detect runtime errors. CodeFlow represents all possible execution paths and the relationships between different statements. It learns dynamic dependencies through execution traces, which reflect the impacts among statements during execution.
  arXiv  Detail & Related papers  (2024-08-05T20:32:00Z)
• 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)
• SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization [51.67317895094664]
  This paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. We propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences.
  arXiv  Detail & Related papers  (2024-01-26T09:23:27Z)
• Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs [65.2379940117181]
  We introduce code prompting, a chain of prompts that transforms a natural language problem into code. We find that code prompting exhibits a high-performance boost for multiple LLMs. Our analysis of GPT 3.5 reveals that the code formatting of the input problem is essential for performance improvement.
  arXiv  Detail & Related papers  (2024-01-18T15:32:24Z)
• Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation [22.219645213202178]
  This paper proposes the "Semantic Chain-of-Thought" approach to intruduce semantic information of code, named SeCoT. We show that SeCoT can achieves state-of-the-art performance, greatly improving the potential for large models and code generation.
  arXiv  Detail & Related papers  (2023-10-16T05:09:58Z)
• Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach [12.214585409361126]
  Large language models (LLMs)- based code generation is a complex and powerful black-box model. We propose a novel causal graph-based representation of the prompt and the generated code. We illustrate the insights that our framework can provide by studying over 3 popular LLMs with over 12 prompt adjustment strategies.
  arXiv  Detail & Related papers  (2023-10-10T14:56:26Z)
• AI Chain on Large Language Model for Unsupervised Control Flow Graph Generation for Statically-Typed Partial Code [21.423928174875844]
  Control Flow Graphs (CFGs) are essential for visualizing, understanding and analyzing program behavior. We propose a novel approach that leverages the error-tolerant and understanding ability of pre-trained Large Language Models (LLMs) to generate CFGs.
  arXiv  Detail & Related papers  (2023-06-01T14:52:59Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• 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)

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.