A Chain of AI-based Solutions for Resolving FQNs and Fixing Syntax Errors in Partial Code

• URL: http://arxiv.org/abs/2306.11981v1
• Date: Wed, 21 Jun 2023 02:13:32 GMT
• Title: A Chain of AI-based Solutions for Resolving FQNs and Fixing Syntax Errors in Partial Code
• Authors: Qing Huang, Jiahui Zhu, Zhenchang Xing, Huan Jin, Changjing Wang, Xiwei Xu
• Abstract summary: API documentation, technical blogs and programming Q&A sites contain numerous partial code that can be reused in programming tasks, but often these code are uncompilable due to unresolved names and syntax errors. We propose the Partial Code Reuse Chain (PCR-Chain) for resolving fully-qualified names (FQNs) and fixing last-mile syntax errors in partial code based on a giant large language model (LLM) like ChatGPT.
• Score: 20.5627916036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: API documentation, technical blogs and programming Q&A sites contain numerous partial code that can be reused in programming tasks, but often these code are uncompilable due to unresolved names and syntax errors. To facilitate partial code reuse, we propose the Partial Code Reuse Chain (PCR-Chain) for resolving fully-qualified names (FQNs) and fixing last-mile syntax errors in partial code based on a giant large language model (LLM) like ChatGPT. Methodologically, PCR-Chain is backed up by the underlying global-level prompt architecture (which combines three design ideas: hierarchical task breakdown, prompt composition, and a mix of prompt-based AI and non-AI units) and the local-level prompt design. Technically, we propose PCR-Chain, which employs in-context learning rather than symbolic, costly training methods. Experimental results demonstrate that in dynamically-typed languages (Python), PCR-Chain outperforms current state-of-the-art (SOTA) 5% accuracy like RING. For statically-type languages (Java), our approach achieves high accuracy of 80.5% in resolving both non-FQNs and last-mile syntax errors, surpassing SOTA methods (RING) that can only address last-mile syntax errors. The correct execution of the unit, module, and PCR-Chain demonstrates the effectiveness of the prompt design, composition, and architecture and opens up possibilities for building software engineering tools based on LLMs, replacing traditional program analysis methods.

Related papers

• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification (UQ) is a critical component of machine learning (ML) applications. We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines. We conduct a large-scale empirical investigation of UQ and normalization techniques across nine tasks, and identify the most promising approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars [11.279507894576213]
  This paper contributes an incremental synthesis that allows early rejection of syntactically incorrect code. We extend the Earley parsing algorithm to allow for left and right quotients of context-free grammars.
  arXiv  Detail & Related papers  (2024-02-28T02:12:47Z)
• Neural Models for Source Code Synthesis and Completion [0.0]
  Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. Current approaches mainly involve hard-coded, rule-based systems based on semantic parsing. We present sequence-to-sequence deep learning models and training paradigms to map NL to general-purpose programming languages.
  arXiv  Detail & Related papers  (2024-02-08T17:10:12Z)
• Recursive Visual Programming [53.76415744371285]
  We propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA.
  arXiv  Detail & Related papers  (2023-12-04T17:27:24Z)
• GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding [52.14832976759585]
  Grammatical error correction (GEC) is an important NLP task that is usually solved with autoregressive sequence-to-sequence models. We propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network. We show that the resulting network improves over previously known non-autoregressive methods for GEC.
  arXiv  Detail & Related papers  (2023-11-14T14:24:36Z)
• LILO: Learning Interpretable Libraries by Compressing and Documenting Code [71.55208585024198]
  We introduce LILO, a neurosymbolic framework that iteratively synthesizes, compresses, and documents code. LILO combines LLM-guided program synthesis with recent algorithmic advances in automated from Stitch. We find that AutoDoc boosts performance by helping LILO's synthesizer to interpret and deploy learned abstractions.
  arXiv  Detail & Related papers  (2023-10-30T17:55:02Z)
• Guess & Sketch: Language Model Guided Transpilation [59.02147255276078]
  Learned transpilation offers an alternative to manual re-writing and engineering efforts. Probabilistic neural language models (LMs) produce plausible outputs for every input, but do so at the cost of guaranteed correctness. Guess & Sketch extracts alignment and confidence information from features of the LM then passes it to a symbolic solver to resolve semantic equivalence.
  arXiv  Detail & Related papers  (2023-09-25T15:42:18Z)
• Code-Style In-Context Learning for Knowledge-Based Question Answering [34.821095476923745]
  We propose a code-style in-context learning method for Knowledge-Based Question Answering (KBQA) Experimental results on three mainstream datasets show that our method dramatically mitigated the formatting error problem in generating logic forms.
  arXiv  Detail & Related papers  (2023-09-09T06:27:00Z)
• 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)
• 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)

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.