Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

• URL: http://arxiv.org/abs/2210.16494v2
• Date: Tue, 13 Jun 2023 17:45:30 GMT
• Title: Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
• Authors: Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu and Saleema Amershi
• Abstract summary: We show that while correctness captures high-value generations, programmers still rate code that fails unit tests as valuable if it reduces the overall effort needed to complete a coding task. We propose a hybrid metric that combines functional correctness and syntactic similarity and show that it achieves a 14% stronger correlation with value.
• Score: 25.726216146776054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code is most often evaluated in terms of their functional correctness (i.e., whether generations pass available unit tests), correctness does not fully capture (e.g., may underestimate) the productivity gains these models may provide. Through a user study with N = 49 experienced programmers, we show that while correctness captures high-value generations, programmers still rate code that fails unit tests as valuable if it reduces the overall effort needed to complete a coding task. Finally, we propose a hybrid metric that combines functional correctness and syntactic similarity and show that it achieves a 14% stronger correlation with value and can therefore better represent real-world gains when evaluating and comparing models.

Related papers

• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes [17.95094238686012]
  Language models (LMs) have exhibited impressive abilities in generating codes from natural language requirements. We highlight the diversity of code generated by LMs as a critical criterion for evaluating their code generation capabilities. We propose a systematic approach to evaluate the diversity of generated code, utilizing various metrics for inter-code similarity as well as functional correctness.
  arXiv  Detail & Related papers  (2024-08-24T07:40:22Z)
• LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation [13.800675921118348]
  We propose a novel interactive workflow TiCoder for guided intent clarification. We present an empirical evaluation of the effectiveness of the workflow to improve code generation accuracy. We observe an average absolute improvement of 45.97% in the pass@1 code generation accuracy for both datasets and across all LLMs within 5 user interactions.
  arXiv  Detail & Related papers  (2024-04-15T19:16:32Z)
• ICE-Score: Instructing Large Language Models to Evaluate Code [7.556444391696562]
  We propose textttICE-Score, a new evaluation metric via instructing large language models for code assessments. Our metric addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences. Our results demonstrate that our metric surpasses state-of-the-art metrics for code generation.
  arXiv  Detail & Related papers  (2023-04-27T16:38:17Z)
• AI-assisted coding: Experiments with GPT-4 [0.22366638308792727]
  GPT-4 can generate tests with substantial coverage, but that many of the tests fail applied to the associated code. These findings suggest that while AI coding tools are very powerful, they still require humans in the loop to ensure validity and accuracy of the results.
  arXiv  Detail & Related papers  (2023-04-25T22:59:01Z)
• Teaching Large Language Models to Self-Debug [62.424077000154945]
  Large language models (LLMs) have achieved impressive performance on code generation. We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
  arXiv  Detail & Related papers  (2023-04-11T10:43:43Z)
• On the Reliability and Explainability of Language Models for Program Generation [15.569926313298337]
  We study the capabilities and limitations of automated program generation approaches. We employ advanced explainable AI approaches to highlight the tokens that significantly contribute to the code transformation. Our analysis reveals that, in various experimental scenarios, language models can recognize code grammar and structural information, but they exhibit limited robustness to changes in input sequences.
  arXiv  Detail & Related papers  (2023-02-19T14:59:52Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)
• ReCode: Robustness Evaluation of Code Generation Models [90.10436771217243]
  We propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt.
  arXiv  Detail & Related papers  (2022-12-20T14:11:31Z)
• Coder Reviewer Reranking for Code Generation [56.80381384717]
  We propose Coder-Reviewer reranking as a method for sampling diverse programs from a code language model and reranking with model likelihood. Experimental results show that Coder-Reviewer reranking leads to consistent and significant improvement over reranking with the Coder model only. Coder-Reviewer reranking is easy to implement by prompting, can generalize to different programming languages, and works well with off-the-shelf hyper parameters.
  arXiv  Detail & Related papers  (2022-11-29T18:56:33Z)
• 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.