PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs

• URL: http://arxiv.org/abs/2401.03855v4
• Date: Thu, 4 Jul 2024 05:40:42 GMT
• Title: PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs
• Authors: Ankit Yadav, Himanshu Beniwal, Mayank Singh,
• Abstract summary: We evaluate two popular benchmarks for Python code generation, analyzing their diversity and difficulty. Our findings unveil a critical bias towards a limited set of programming concepts, neglecting most of the other concepts entirely. We propose a novel benchmark, PythonSaga, featuring 185 hand-crafted prompts on a balanced representation of 38 programming concepts.
• Score: 1.9207412600219353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Driven by the surge in code generation using large language models (LLMs), numerous benchmarks have emerged to evaluate these LLMs capabilities. We conducted a large-scale human evaluation of HumanEval and MBPP, two popular benchmarks for Python code generation, analyzing their diversity and difficulty. Our findings unveil a critical bias towards a limited set of programming concepts, neglecting most of the other concepts entirely. Furthermore, we uncover a worrying prevalence of easy tasks, potentially inflating model performance estimations. To address these limitations, we propose a novel benchmark, PythonSaga, featuring 185 hand-crafted prompts on a balanced representation of 38 programming concepts across diverse difficulty levels. The robustness of our benchmark is demonstrated by the poor performance of existing Code-LLMs.

Related papers

• mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation [28.531581489405745]
  mHumanEval is an extended benchmark supporting prompts in over 200 natural languages. We provide expert human translations for 15 diverse natural languages (NLs) We conclude by analyzing the multilingual code generation capabilities of state-of-the-art (SOTA) Code LLMs.
  arXiv  Detail & Related papers  (2024-10-19T08:44:26Z)
• HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks [25.959032350818795]
  HumanEval-V is a benchmark designed to evaluate Large Language Models' visual understanding and reasoning capabilities through code generation. HumanEval-V includes 108 carefully crafted, entry-level Python coding tasks derived from platforms like CodeForces and Stack Overflow. We evaluate 19 state-of-the-art LMMs using HumanEval-V, uncovering significant challenges.
  arXiv  Detail & Related papers  (2024-10-16T09:04:57Z)
• CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution [50.7413285637879]
  The CRUXEVAL-X code reasoning benchmark contains 19 programming languages. It comprises at least 600 subjects for each language, along with 19K content-consistent tests in total. Even a model trained solely on Python can achieve at most 34.4% Pass@1 in other languages.
  arXiv  Detail & Related papers  (2024-08-23T11:43:00Z)
• What's Wrong with Your Code Generated by Large Language Models? An Extensive Study [80.18342600996601]
  Large language models (LLMs) produce code that is shorter yet more complicated as compared to canonical solutions. We develop a taxonomy of bugs for incorrect codes that includes three categories and 12 sub-categories, and analyze the root cause for common bug types. We propose a novel training-free iterative method that introduces self-critique, enabling LLMs to critique and correct their generated code based on bug types and compiler feedback.
  arXiv  Detail & Related papers  (2024-07-08T17:27:17Z)
• The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models [94.31327813151208]
  BiGGen Bench is a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks. A key feature of the BiGGen Bench is its use of instance-specific evaluation criteria, closely mirroring the nuanced discernment of human evaluation.
  arXiv  Detail & Related papers  (2024-06-09T12:30:30Z)
• MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation [18.1643331912182]
  Large language models (LLMs) have greatly improved code generation, specifically at the function level. Our study analyzed two common benchmarks, HumanEval and MBPP, and found that these might not thoroughly evaluate LLMs' code generation capacities. To resolve this, we introduce the Mostly Hard Python Problems dataset, consisting of 210 unique human-curated problems.
  arXiv  Detail & Related papers  (2024-05-19T03:08:02Z)
• Low-Cost Language Models: Survey and Performance Evaluation on Python Code Generation [0.0]
  Large Language Models (LLMs) have become a popular choice for many Natural Language Processing (NLP) tasks. LLMs' substantial computational and memory requirements often make them inaccessible to users with limited resources. This paper focuses on very low-cost models which offer a more accessible alternative to resource-intensive LLMs.
  arXiv  Detail & Related papers  (2024-04-17T08:16:48Z)
• L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models [102.00201523306986]
  We present L2CEval, a systematic evaluation of the language-to-code generation capabilities of large language models (LLMs) We analyze the factors that potentially affect their performance, such as model size, pretraining data, instruction tuning, and different prompting methods. In addition to assessing model performance, we measure confidence calibration for the models and conduct human evaluations of the output programs.
  arXiv  Detail & Related papers  (2023-09-29T17:57:00Z)
• MMBench: Is Your Multi-modal Model an All-around Player? [114.45702807380415]
  We propose MMBench, a benchmark for assessing the multi-modal capabilities of vision-language models. MMBench is meticulously curated with well-designed quality control schemes. MMBench incorporates multiple-choice questions in both English and Chinese versions.
  arXiv  Detail & Related papers  (2023-07-12T16:23:09Z)
• Measuring Coding Challenge Competence With APPS [54.22600767666257]
  We introduce APPS, a benchmark for code generation. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. Recent models such as GPT-Neo can pass approximately 15% of the test cases of introductory problems.
  arXiv  Detail & Related papers  (2021-05-20T17:58:42Z)

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.