Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol

• URL: http://arxiv.org/abs/2503.05860v1
• Date: Fri, 07 Mar 2025 18:44:32 GMT
• Title: Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol
• Authors: Roham Koohestani, Philippe de Bekker, Maliheh Izadi,
• Abstract summary: We review 173 studies and identify 204 AI4SE benchmarks. We classify these benchmarks, analyze their limitations, and expose gaps in practices.<n>Based on our review, we created BenchScout, a semantic search tool to find relevant benchmarks.<n>We then evaluated ten state-of-the-art code language models on HumanEval, HumanEvalPlus, and HumanEvalNext. On HumanEvalNext, models showed a pass@1 score reduction of 31.22% and 19.94% compared to HumanEval and HumanEvalPlus, respectively.
• Score: 2.3759432635713895
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Benchmarks are essential for consistent evaluation and reproducibility. The integration of Artificial Intelligence into Software Engineering (AI4SE) has given rise to numerous benchmarks for tasks such as code generation and bug fixing. However, this surge presents challenges: (1) scattered benchmark knowledge across tasks, (2) difficulty in selecting relevant benchmarks, (3) the absence of a uniform standard for benchmark development, and (4) limitations of existing benchmarks. In this paper, we review 173 studies and identify 204 AI4SE benchmarks. We classify these benchmarks, analyze their limitations, and expose gaps in practices. Based on our review, we created BenchScout, a semantic search tool to find relevant benchmarks, using automated clustering of the contexts from associated studies. We conducted a user study with 22 participants to evaluate BenchScout's usability, effectiveness, and intuitiveness which resulted in average scores of 4.5, 4.0, and 4.1 out of 5. To advance benchmarking standards, we propose BenchFrame, a unified method to enhance benchmark quality. As a case study, we applied BenchFrame to the HumanEval benchmark and addressed its main limitations. This led to HumanEvalNext, featuring (1) corrected errors, (2) improved language conversion, (3) expanded test coverage, and (4) increased difficulty. We then evaluated ten state-of-the-art code language models on HumanEval, HumanEvalPlus, and HumanEvalNext. On HumanEvalNext, models showed a pass@1 score reduction of 31.22% and 19.94% compared to HumanEval and HumanEvalPlus, respectively.

Related papers

• Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks [47.40240774236047]
  We compare four Chat Llama 2 models against extensive human preferences on more than 11k single-turn and 2k multi-turn dialogues from over 2k human annotators. Most NLP benchmarks strongly correlate with human evaluations, suggesting that cheaper, automated metrics can serve as surprisingly reliable predictors of human preferences.
  arXiv  Detail & Related papers  (2025-02-24T01:01:02Z)
• How Should We Build A Benchmark? Revisiting 274 Code-Related Benchmarks For LLMs [60.25940747590386]
  We propose How2Bench, which is comprised of a 55-criteria checklist as a set of guidelines to govern the development of code-related benchmarks comprehensively. We profiled 274 benchmarks released within the past decade and found concerning issues. Nearly 70% of the benchmarks did not take measures for data quality assurance; over 10% did not even open source or only partially open source.
  arXiv  Detail & Related papers  (2025-01-18T09:51:57Z)
• BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices [28.70453947993952]
  We develop an assessment framework considering 46 best practices across an AI benchmark's lifecycle and evaluate 24 AI benchmarks against it. We find that there exist large quality differences and that commonly used benchmarks suffer from significant issues.
  arXiv  Detail & Related papers  (2024-11-20T02:38:24Z)
• 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)
• Introducing v0.5 of the AI Safety Benchmark from MLCommons [101.98401637778638]
  This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models.
  arXiv  Detail & Related papers  (2024-04-18T15:01:00Z)
• ARB: Advanced Reasoning Benchmark for Large Language Models [94.37521840642141]
  We introduce ARB, a novel benchmark composed of advanced reasoning problems in multiple fields. As a subset of ARB, we introduce a challenging set of math and physics problems which require advanced symbolic reasoning and domain knowledge. We evaluate recent models such as GPT-4 and Claude on ARB and demonstrate that current models score well below 50% on more demanding tasks.
  arXiv  Detail & Related papers  (2023-07-25T17:55:19Z)
• AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models [122.63704560157909]
  We introduce AGIEval, a novel benchmark designed to assess foundation model in the context of human-centric standardized exams. We evaluate several state-of-the-art foundation models, including GPT-4, ChatGPT, and Text-Davinci-003. GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.
  arXiv  Detail & Related papers  (2023-04-13T09:39:30Z)
• Benchmarks for Automated Commonsense Reasoning: A Survey [0.0]
  More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of AI systems. This paper surveys the development and uses of AI commonsense benchmarks.
  arXiv  Detail & Related papers  (2023-02-09T16:34:30Z)
• What Will it Take to Fix Benchmarking in Natural Language Understanding? [30.888416756627155]
  We lay out four criteria that we argue NLU benchmarks should meet. Restoring a healthy evaluation ecosystem will require significant progress in the design of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-05T20:36:11Z)

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.