paper-with-me

Papers

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

2024-10-30 · Jia Li, Ge Li, Xuanming Zhang, YunFei Zhao, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li

How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCodeBench-2403, containing 275 samples from 25 repositories. (2) A domain taxonomy and domain labels. Based on the statistics of open-source communities, we design a programming domain taxonomy consisting of 10 popular domains. Based on the taxonomy, we annotate each sample in EvoCodeBench with a domain label. (3) Domain-specific evaluations. Besides the Pass@k, we compute the Domain-Specific Improvement (DSI) and define LLMs' comfort and strange domains. These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs. We evaluate 8 popular LLMs (e.g., gpt-4, DeepSeek Coder) on EvoCodeBench and summarize some insights. EvoCodeBench reveals the actual abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 on EvoCodeBench-2403 is only 20.74%. Besides, we evaluate LLMs in different domains and discover their comfort and strange domains. For example, gpt-4 performs best in most domains but falls behind others in the Internet domain. StarCoder 2-15B unexpectedly performs well in the Database domain and even outperforms 33B LLMs. EvoCodeBench has been released.

📄 PDF Abstract BibTeX arXiv:2410.22821

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationFairness

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Attention 설명 없음

Similar Papers 제목 키워드 기반

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories

2024-03-31 · Jia Li, Ge Li, Xuanming Zhang, Yihong Dong 외

How to evaluate Large Language Models (LLMs) in code generation is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities …

Code Generation

EvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems

2026-02-10 · Wentao Zhang, Jianfeng Wang, Liheng Liang, Yilei Zhao 외 arxiv

As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. Howev…

Code Generation

Knowledge Graph Based Repository-Level Code Generation

2025-05-20 · Mihir Athale, Vishal Vaddina

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle…

Code GenerationCode SearchNatural Language QueriesRetrieval

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

2024-08-07 · Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu 외

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a r…

HumanEvalmbppRetrieval

Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM

2024-03-28 · Chunqiu Steven Xia, Yinlin Deng, Lingming Zhang

LLMs have become the go-to choice for code generation tasks, with an exponential increase in the training, development, and usage of LLMs specifically for code generation. To evaluate the ability of LLMs on code, both ac…

Code GenerationHumanEvalInstruction FollowingProgram Synthesis