← Search

Mengfei Yang

2 accepted papers

2024

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories

ACL 2024findings

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs.To address the knowledge gap, we propose a new benchmark…

2024

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models

ACL 2024findings

Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data, leading to LLMs being mor…