paper-with-me

Papers

Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation

2022-12-06 · Anjan Karmakar, Julian Aron Prenner, Marco D'Ambros, Romain Robbes

The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must be systematically subjected to multiple and diverse evaluation studies. In this work, we evaluate the code synthesis capabilities of the Codex model based on a set of 115 Python problem statements from a popular competitive programming portal: HackerRank. Our evaluation shows that Codex is indeed proficient in Python, solving 96% of the problems in a zero-shot setting, and 100% of the problems in a few-shot setting. However, Codex exhibits clear signs of generating memorized code based on our evaluation. This is alarming, especially since the adoption and use of such models could directly impact how code is written and produced in the foreseeable future. With this in mind, we further discuss and highlight some of the prominent risks associated with large-scale models of source code. Finally, we propose a framework for code-synthesis evaluation using variations of problem statements based on mutations.

📄 PDF Abstract BibTeX arXiv:2212.02684

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Similar Papers 제목 키워드 기반

HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

2024-12-02 · Lajos Muzsai, David Imolai, András Lukács

We introduce HackSynth, a novel Large Language Model (LLM)-based agent capable of autonomous penetration testing. HackSynth's dual-module architecture includes a Planner and a Summarizer, which enable it to generate comm…

Language ModelingLanguage ModellingLarge Language Model

HackerRank-ASTRA: Evaluating Correctness & Consistency of Large Language Models on cross-domain multi-file project problems

2025-01-31 · Jun Xing, Mayur Bhatia, Sahil Phulwani, Darshan Suresh 외

Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problem…

Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces

2025-03-30 · Max Hort, Leon Moonen

Software is used in critical applications in our day-to-day life and it is important to ensure its correctness. One popular approach to assess correctness is to evaluate software on tests. If a test fails, it indicates a…

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

2022-11-18 · Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang 외

We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First,…

Code GenerationMemorization

NeuCODEX: Edge-Cloud Co-Inference with Spike-Driven Compression and Dynamic Early-Exit

2025-09-23 · Maurf Hassan, Steven Davy, Muhammad Zawish, Owais Bin Zuber 외 arxiv

Spiking Neural Networks (SNNs) offer significant potential for enabling energy-efficient intelligence at the edge. However, performing full SNN inference at the edge can be challenging due to the latency and energy const…