HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation

• URL: http://arxiv.org/abs/2412.21199v2
• Date: Tue, 31 Dec 2024 08:20:42 GMT
• Title: HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation
• Authors: Zhaojian Yu, Yilun Zhao, Arman Cohan, Xiao-Ping Zhang,
• Abstract summary: We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks.
• Score: 28.295580042013547
• License:
• Abstract: We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs on self-invoking code generation. Second, from the analysis of experimental results over twenty LLMs on our benchmarks, we have two important observations: (i) Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks. For example, o1-mini achieves 96.2% pass@1 on HumanEval but only 76.2% on HumanEval Pro. (ii) On self-invoking code generation task, the instruction-tuned models demonstrate only marginal improvements compared to the base models. Third, we disclose the types of failure modes that exist in our evaluation results. All these results underscore the need for further advancements in self-invoking code generation tasks and provide a new direction for future research on enhancing LLMs' code reasoning capabilities.

Related papers

• How to Get Your LLM to Generate Challenging Problems for Evaluation [33.625052642068624]
  CHASE is a unified framework to synthetically generate challenging problems using Large Language Models. We implement CHASE to create evaluation benchmarks across three diverse domains. The performance of state-of-the-art LLMs on these synthetic benchmarks lies in the range of 40-60% accuracy.
  arXiv  Detail & Related papers  (2025-02-20T16:09:55Z)
• Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation [55.21013307734612]
  AoPS-Instruct is a dataset of more than 600,000 high-quality QA pairs. LiveAoPSBench is an evolving evaluation set with timestamps, derived from the latest forum data. Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning.
  arXiv  Detail & Related papers  (2025-01-24T06:39:38Z)
• 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)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers [44.28269395385471]
  We study whether gains on existing benchmarks or more preferred LLM responses translate to programmer productivity when coding with LLMs. We introduce RealHumanEval, a web interface to measure the ability of LLMs to assist programmers. Despite static benchmarks not incorporating humans-in-the-loop, we find that improvements in benchmark performance lead to increased programmer productivity.
  arXiv  Detail & Related papers  (2024-04-03T15:20:57Z)
• CYCLE: Learning to Self-Refine the Code Generation [19.71833229434497]
  We propose CYCLE framework, learning to self-refine the faulty generation according to the available feedback. We implement four variants of CYCLE with varied numbers of parameters across 350M, 1B, 2B, and 3B benchmarks. The results reveal that CYCLE successfully maintains, sometimes improves, the quality of one-time code generation, while significantly improving the self-refinement capability of code LMs.
  arXiv  Detail & Related papers  (2024-03-27T16:45:02Z)
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code [34.03774442237902]
  Large Language Models applied to code-related applications have emerged as a prominent field. Existing evaluation benchmarks (e.g., HumanEval, MBPP) are no longer sufficient for assessing their capabilities. We propose LiveCodeBench, a comprehensive and contamination-free evaluation of LLMs for code.
  arXiv  Detail & Related papers  (2024-03-12T17:58:04Z)
• LLM-Assisted Code Cleaning For Training Accurate Code Generators [53.087019724256606]
  We investigate data quality for code and find that making the code more structured and readable leads to improved code generation performance of the system. We build a novel data-cleaning pipeline that uses these principles to transform existing programs. We evaluate our approach on two challenging algorithmic code generation benchmarks and find that fine-tuning CodeLLaMa-7B improves the performance by up to 30% compared to fine-tuning on the original dataset.
  arXiv  Detail & Related papers  (2023-11-25T02:45:50Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)
• 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.