@inproceedings{yadav-etal-2024-pythonsaga,
title = "{P}ython{S}aga: Redefining the Benchmark to Evaluate Code Generating {LLM}s",
author = "Yadav, Ankit and
Beniwal, Himanshu and
Singh, Mayank",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.996/",
doi = "10.18653/v1/2024.findings-emnlp.996",
pages = "17113--17126",
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 that can inflate model performance estimations. To address these limitations, we propose a novel benchmark, *PythonSaga*, featuring 185 hand-crafted prompts in 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. The code and data set are openly available to the NLP community at this [URL](https://github.com/PythonSaga/PythonSaga)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2024-pythonsaga">
<titleInfo>
<title>PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Himanshu</namePart>
<namePart type="family">Beniwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 that can inflate model performance estimations. To address these limitations, we propose a novel benchmark, *PythonSaga*, featuring 185 hand-crafted prompts in 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. The code and data set are openly available to the NLP community at this [URL](https://github.com/PythonSaga/PythonSaga).</abstract>
<identifier type="citekey">yadav-etal-2024-pythonsaga</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.996</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.996/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>17113</start>
<end>17126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs
%A Yadav, Ankit
%A Beniwal, Himanshu
%A Singh, Mayank
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F yadav-etal-2024-pythonsaga
%X 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 that can inflate model performance estimations. To address these limitations, we propose a novel benchmark, *PythonSaga*, featuring 185 hand-crafted prompts in 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. The code and data set are openly available to the NLP community at this [URL](https://github.com/PythonSaga/PythonSaga).
%R 10.18653/v1/2024.findings-emnlp.996
%U https://aclanthology.org/2024.findings-emnlp.996/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.996
%P 17113-17126
Markdown (Informal)
[PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs](https://aclanthology.org/2024.findings-emnlp.996/) (Yadav et al., Findings 2024)
ACL