Showing cs.SEShow all
3 papers · 1 filter
cs.SE2025
Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations
Wei Ma, Yixiao Yang, Jingquan Ge +2
Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emo…
cs.SE2025
Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
Wei Ma, Yixiao Yang, Qiang Hu +8
Applications of Large Language Models~(LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and mult…
cs.SE2020
Corrigendum and Supplement to "Improve Language Modelling for Code Completion through Learning General Token Repetition of Source Code (with Optimized Memory)"
Yixiao Yang
This paper is written because I receive several inquiry emails saying it is hard to achieve good results when applying token repetition learning techniques. If REP (proposed by me)…