| 1 |
JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks |
提出JailBreakV基准以评估多模态大语言模型的安全性 |
large language model multimodal |
|
|
| 2 |
Testing the Effect of Code Documentation on Large Language Model Code Understanding |
探讨代码文档对大型语言模型代码理解的影响 |
large language model |
|
|
| 3 |
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers |
提出RealHumanEval以评估大型语言模型对程序员的支持能力 |
large language model |
|
|
| 4 |
Vocabulary Attack to Hijack Large Language Model Applications |
提出词汇攻击以劫持大型语言模型应用 |
large language model |
|
|
| 5 |
Integrating Explanations in Learning LTL Specifications from Demonstrations |
提出结合LLM与优化方法以学习LTL规范 |
large language model |
|
|
| 6 |
I-Design: Personalized LLM Interior Designer |
提出I-Design以解决非专业人士的室内设计难题 |
large language model |
|
|
| 7 |
AI-Tutoring in Software Engineering Education |
通过GPT-3.5-Turbo模型提升软件工程教育中的AI辅导效果 |
large language model |
|
|
| 8 |
NL2KQL: From Natural Language to Kusto Query |
提出NL2KQL框架以将自然语言查询转化为Kusto查询 |
large language model |
|
|