Galapagos: Automated N-Version Programming with LLMs

• URL: http://arxiv.org/abs/2408.09536v2
• Date: Mon, 13 Jan 2025 15:25:37 GMT
• Title: Galapagos: Automated N-Version Programming with LLMs
• Authors: Javier Ron, Diogo Gaspar, Javier Cabrera-Arteaga, Benoit Baudry, Martin Monperrus,
• Abstract summary: We propose the automated generation of program variants using large language models. We design, develop and evaluate Gal'apagos: a tool for generating program variants. We evaluate Gal'apagos by creating N-Version components of real-world C code.
• Score: 10.573037638807024
• License:
• Abstract: N-Version Programming is a well-known methodology for developing fault-tolerant systems. It achieves fault detection and correction at runtime by adding diverse redundancy into programs, minimizing fault mode overlap between redundant program variants. In this work, we propose the automated generation of program variants using large language models. We design, develop and evaluate Gal\'apagos: a tool for generating program variants using LLMs, validating their correctness and equivalence, and using them to assemble N-Version binaries. We evaluate Gal\'apagos by creating N-Version components of real-world C code. Our original results show that Gal\'apagos can produce program variants that are proven to be functionally equivalent, even when the variants are written in a different programming language. Our systematic diversity measurement indicates that functionally equivalent variants produced by Gal\'apagos, are statically different after compilation, and present diverging internal behavior at runtime. We demonstrate that the variants produced by Gal\'apagos can protect C code against real miscompilation bugs which affect the Clang compiler. Overall, our paper shows that producing N-Version software can be drastically automated by advanced usage of practical formal verification and generative language models.

Related papers

• VeCoGen: Automating Generation of Formally Verified C Code with Large Language Models [1.6249267147413524]
  VeCoGen is a novel tool that combines Large Language Models (LLMs) with formal verification to automate the generation of formally verified C programs. VeCoGen takes a formal specification in ISO/ISO C Specification Language (ACSL), a natural language specification, and a set of test cases to attempt to generate a program.
  arXiv  Detail & Related papers  (2024-11-28T17:12:21Z)
• Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages [21.18996339478024]
  We introduce emphsynthetic programming elicitation and compilation (SPEAC) SPEAC produces syntactically correct programs more frequently and without sacrificing semantic correctness. We empirically evaluate the performance of SPEAC in a case study for the UCLID5 formal verification language.
  arXiv  Detail & Related papers  (2024-06-05T22:16:19Z)
• NExT: Teaching Large Language Models to Reason about Code Execution [50.93581376646064]
  Large language models (LLMs) of code are typically trained on the surface textual form of programs. We propose NExT, a method to teach LLMs to inspect the execution traces of programs and reason about their run-time behavior.
  arXiv  Detail & Related papers  (2024-04-23T01:46:32Z)
• Evolutionary Generative Fuzzing for Differential Testing of the Kotlin Compiler [14.259471945857431]
  We investigate the effectiveness of differential testing in finding bugs within the Kotlin compilers developed at JetBrains. We propose a black-box generative approach that creates input programs for the K1 and K2 compilers. Our case study shows that the proposed approach effectively detects bugs in K1 and K2; these bugs have been confirmed and (some) fixed by JetBrains developers.
  arXiv  Detail & Related papers  (2024-01-12T16:01:12Z)
• AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection [69.79627042058048]
  AdaCCD is a novel cross-lingual adaptation method that can detect cloned codes in a new language without annotations in that language. We evaluate the cross-lingual adaptation results of AdaCCD by constructing a multilingual code clone detection benchmark consisting of 5 programming languages.
  arXiv  Detail & Related papers  (2023-11-13T12:20:48Z)
• 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)
• SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly [6.080751346188323]
  This paper presents SLaDe, a Small Language model Decompiler based on a sequence-to-sequence transformer trained over real-world code. We utilize type-inference to generate programs that are more readable and accurate than standard analytic and recent neural approaches.
  arXiv  Detail & Related papers  (2023-05-21T17:31:39Z)
• Teaching Large Language Models to Self-Debug [62.424077000154945]
  Large language models (LLMs) have achieved impressive performance on code generation. We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
  arXiv  Detail & Related papers  (2023-04-11T10:43:43Z)
• Fault-Aware Neural Code Rankers [64.41888054066861]
  We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it. Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
  arXiv  Detail & Related papers  (2022-06-04T22:01:05Z)
• Natural Language to Code Translation with Execution [82.52142893010563]
  Execution result--minimum Bayes risk decoding for program selection. We show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks.
  arXiv  Detail & Related papers  (2022-04-25T06:06:08Z)

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.