most citedCurriculum Demonstration Selection for In-Context Learning

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.SE2025

Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis

Dong Huang, Mingzhe Du, Jie M. Zhang +4

Test oracle generation in non-regression testing is a longstanding challenge in software engineering, where the goal is to produce oracles that can accurately determine whether a f…

cs.SE2025

Benchmarking LLMs for Unit Test Generation from Real-World Functions

Dong Huang, Jie M. Zhang, Mark Harman +3

Recently, large language models (LLMs) have shown great promise in automating unit test generation, significantly reducing the manual effort required by developers. To effectively…

cs.CL2025

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Yuhao Qing, Boyu Zhu, Mingzhe Du +9

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To addre…

cs.SE2025

CodeArena: A Collective Evaluation Platform for LLM Code Generation

Mingzhe Du, Anh Tuan Luu, Bin Ji +5

Large Language Models (LLMs) have reshaped code generation by synergizing their exceptional comprehension of natural language and programming syntax, thereby substantially boosting…

cs.CL20241 cited

Curriculum Demonstration Selection for In-Context Learning

Duc Anh Vu, Nguyen Tran Cong Duy, Xiaobao Wu +4

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to eli…

cs.CL2024

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Xiaobao Wu, Liangming Pan, Yuxi Xie +7

Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly co…