检索结果-内蒙古大学图书馆

CODEFLOW: Program Behavior Prediction with Dynamic Dependencies Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Le, Cuong Chi Phan, Hoang Nhat Phan, Huy Nhat Nguyen, Tien N. Bui, Nghi D.Q. FPT Software AI Center Viet Nam Nanyang Technological University Singapore University of Texas Dallas United States

Predicting program behavior without execution is a critical task in software engineering. Existing models often fall short in capturing the dynamic dependencies among program elements. To address this, we present CODEFLOW, a novel machine learning-based approach that predicts code coverage and detects runtime errors by learning both static and dynamic dependencies within the code. By using control flow graphs (CFGs), CODEFLOW effectively represents all possible execution paths and the statistic relations between different statements, providing a more comprehensive understanding of program behaviors. CODEFLOW constructs CFGs to represent possible execution paths and learns vector representations (embeddings) for CFG nodes, capturing static control-flow dependencies. Additionally, it learns dynamic dependencies by leveraging execution traces, which reflect the impacts among statements during execution. This combination enables CODEFLOW to accurately predict code coverage and identify runtime errors. Our empirical evaluation demonstrates that CODEFLOW significantly improves code coverage prediction accuracy and effectively localizes runtime errors, outperforming state-of-the-art models. © 2024, CC0.

关键词： coding errors

Can GPT-3.5 Generate and Code Discharge Summaries?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Falis, Matúš Gema, Aryo Pradipta Dong, Hang Daines, Luke Basetti, Siddharth Holder, Michael Penfold, Rose S. Birch, Alexandra Alex, Beatrice School of Informatics The University of Edinburgh Edinburgh United Kingdom Department of Computer Science University of Exeter Exeter United Kingdom Centre for Population Health Sciences Usher Institute The University of Edinburgh Edinburgh United Kingdom Department of Research Development and Innovation National Health Service Highland Inverness United Kingdom Ageing and Health Usher Institute The University of Edinburgh Edinburgh United Kingdom Advanced Care Research Centre The University of Edinburgh Edinburgh United Kingdom Edinburgh Futures Institute The University of Edinburgh Edinburgh United Kingdom School of Literatures Languages and Cultures The University of Edinburgh Edinburgh United Kingdom

Objective: To investigate GPT-3.5 in generating and coding medical documents with ICD-10 codes for data augmentation on low-resources labels. Materials and Methods: Employing GPT-3.5 we generated and coded 9,606 discharge summaries based on lists of ICD-10 code descriptions of patients with infrequent (or generation) codes within the MIMIC-IV dataset. Combined with the baseline training set, this formed an augmented training set. Neural coding models were trained on baseline and augmented data and evaluated on a MIMIC-IV test set. We report micro- and macro-F1 scores on the full codeset, generation codes, and their families. Weak Hierarchical Confusion Matrices determined within-family and outsideof- family coding errors in the latter codesets. The coding performance of GPT-3.5 was evaluated on prompt-guided self-generated data and real MIMIC-IV data. Clinicians evaluated the clinical acceptability of the generated documents. Results: Data augmentation results in slightly lower overall model performance but improves performance for the generation candidate codes and their families, including one absent from the baseline training data. Augmented models display lower out-of-family error rates. GPT-3.5 identifies ICD-10 codes by their prompted descriptions, but underperforms on real data. Evaluators highlight the correctness of generated concepts while suffering in variety, supporting information, and narrative. Discussion and Conclusion: While GPT-3.5 alone given our prompt setting is unsuitable for ICD-10 coding, it supports data augmentation for training neural models. Augmentation positively affects generation code families but mainly benefits codes with existing examples. Augmentation reduces out-of-family errors. Documents generated by GPT-3.5 state prompted concepts correctly but lack variety, and authenticity in narratives. © 2024, CC BY.

关键词： coding errors

Quantum Codes from Twisted Unitary t-groups

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kubischta, Eric Teixeira, Ian Joint Center for Quantum Information and Computer Science NIST/University of Maryland College ParkMD20742 United States

We introduce twisted unitary t-groups, a generalization of unitary t-groups under a twisting by an irreducible representation. We then apply representation theoretic methods to the Knill-Laflamme error correction conditions to show that twisted unitary t-groups automatically correspond to quantum codes with distance d = t+1. By construction these codes have many transversal gates, which naturally do not spread errors and thus are useful for fault tolerance. Copyright © 2024, The Authors. All rights reserved.

关键词： coding errors

CRACKING THE CODE: EVALUATING ZERO-SHOT PROMPTING METHODS FOR PROVIDING PROGRAMMING FEEDBACK

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ippisch, Niklas Haensch, Anna-Carolina Simson, Jan Beck, Jacob Herklotz, Markus Schierholz, Malte

Despite the growing use of large language models (LLMs) for providing feedback, limited research has explored how to achieve high-quality feedback. This case study introduces an evaluation framework to assess different zero-shot prompt engineering methods. We varied the prompts systematically and analyzed the provided feedback on programming errors in R. The results suggest that prompts suggesting a stepwise procedure increase the precision, while omitting explicit specifications about which provided data to analyze improves error identification. Copyright © 2024, The Authors. All rights reserved.

关键词： coding errors

Class of codes correcting absorptions and emissions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Aydin, Arda Barg, Alexander ISR and Dept. of ECE University of Maryland College ParkMD20742 United States QuICS NIST UMD

We construct a general family of quantum codes that protect against all emission, absorption, dephasing, and raising/lowering errors up to an arbitrary fixed order. Such codes are known in the literature as absorption-emission (AE) codes. We derive simplified error correction conditions for a general AE code and show that any permutation-invariant code that corrects ≤ t errors can be mapped to an AE code that corrects up to order-t transitions. Carefully tuning the parameters of permutationally invariant codes, we construct several examples of efficient AE codes, hosted in systems with low total angular momentum. Our results also imply that spin codes can be mapped to AE codes, enabling us to characterize logical operators for certain subclasses of such codes. Copyright © 2024, The Authors. All rights reserved.

关键词： coding errors

Using a Feedback Loop for LLM-based Infrastructure as Code Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Palavalli, Mayur Amarnath Santolucito, Mark Irvington High School FremontCA United States Barnard College Columbia University New YorkNY United States

Code generation with Large Language Models (LLMs) has helped to increase software developer productivity in coding tasks, but has yet to have significant impact on the tasks of software developers that surround this code. In particular, the challenge of infrastructure management remains an open question. We investigate the ability of an LLM agent to construct infrastructure using the Infrastructure as Code (IaC) paradigm. We particularly investigate the use of a feedback loop that returns errors and warnings on the generated IaC to allow the LLM agent to improve the code. We find that, for each iteration of the loop, its effectiveness decreases exponentially until it plateaus at a certain point and becomes ineffective. © 2024, CC BY.

关键词： coding errors

AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Demirok, Basak Kutlu, Mucahid TOBB University of Economics and Technology Turkey Qatar University Qatar

With the rapid advancement of LLM models, they have become widely useful in various fields. While these AI systems can be used for code generation, significantly simplifying and accelerating the tasks of developers, their use for students to do assignments has raised ethical questions in the field of education. In this context, determining the author of a particular code becomes important. In this study, we introduce AIGCodeSet, a dataset for AI-generated code detection tasks, specifically for the Python programming language. We obtain the problem descriptions and humanwritten codes from the CodeNet dataset. Using the problem descriptions, we generate AIwritten codes with CodeLlama 34B, Codestral 22B, and Gemini 1.5 Flash models in three approaches: i) generating code from the problem description alone, ii) generating code using the description along with human-written source code containing runtime errors, and iii) generating code using the problem description and human-written code that resulted in wrong answers. Lastly, we conducted a post-processing step to eliminate LLM output irrelevant to code snippets. Overall, AIGCodeSet consists of 2,828 AI-generated and 4,755 human-written code snippets. We share our code with the research community to support studies on this important topic and provide performance results for baseline AI-generated code detection methods. © 2024, CC BY.

关键词： coding errors

CODECLOAK: A METHOD FOR MITIGATING CODE LEAKAGE BY LLM CODE ASSISTANTS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Noah, Amit Finkman Shapira, Avishag Kochva, Eden Bar Maimon, Inbar Mimran, Dudu Elovici, Yuval Shabtai, Asaf Department of Software and Information Systems Engineering Ben-Gurion University of The Negev

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer’s codebase. While beneficial, the use of these tools can inadvertently expose the developer’s proprietary code to the code assistant service provider during the development process. In this work, we propose a method to mitigate the risk of code leakage when using LLM-based code assistants. CodeCloak is a novel deep reinforcement learning agent that manipulates the prompts before sending them to the code assistant service. CodeCloak aims to achieve the following two contradictory goals: (i) minimizing code leakage, while (ii) preserving relevant and useful suggestions for the developer. Our evaluation, employing StarCoder and Code Llama, LLM-based code assistants models, demonstrates CodeCloak’s effectiveness on a diverse set of code repositories of varying sizes, as well as its transferability across different models. We also designed a method for reconstructing the developer’s original codebase from code segments sent to the code assistant service (i.e., prompts) during the development process, to thoroughly analyze code leakage risks and evaluate the effectiveness of CodeCloak under practical development scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： coding errors

Quantum LDPC codes from intersecting subsets

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ostrev, Dimiter Institute of Communications and Navigation Wessling82234 Germany

This paper introduces a construction of quantum CSS codes from a tuple of component CSS codes and two collections of subsets. The resulting codes have parallelizable encoding and syndrome measurement circuits and built-in redundancy in the syndrome measurements. In a certain subfamily of the general construction, the resulting codes are related to a natural generalization of classical Reed-Muller codes, and this leads to formulas for the distance of the quantum code as well as for the distance of the associated classical code that protects against errors in the syndrome. The paper gives a number of examples of codes with block size 2m, m = 3, . . ., 9, and with syndrome measurements involving 2, 4 or 8 qubits. These include codes for which the distance exceeds the syndrome measurement weight, as well as codes which provide asymmetric protection against bit flip and phase flip errors. Copyright © 2023, The Authors. All rights reserved.

关键词： coding errors