| 1 |
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models |
SpeechGuard:揭示多模态大语言模型在对抗攻击下的脆弱性并提出防御措施 |
large language model multimodal instruction following |
|
|
| 2 |
A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine |
综述医学领域大语言模型与多模态大语言模型的发展、应用与挑战 |
large language model multimodal |
|
|
| 3 |
Assisted Debate Builder with Large Language Models |
ADBL2:基于大语言模型的辅助辩论构建工具,提升论证挖掘性能。 |
large language model |
|
|
| 4 |
Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline |
提出MSAIRS任务与数据集,研究表情包对社交媒体多模态情感与意图的影响 |
multimodal |
✅ |
|
| 5 |
Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models |
利用新语素和大型语言模型增强性别包容性机器翻译 |
large language model |
|
|
| 6 |
Alignment Helps Make the Most of Multimodal Data |
强调多模态数据对齐,提升政治科学研究分析效果 |
multimodal |
|
|
| 7 |
Stylometric Watermarks for Large Language Models |
提出基于文体学特征的水印方法,用于区分大型语言模型生成文本与人类创作文本 |
large language model |
|
|
| 8 |
Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs |
提出一种生成式评估方法,用于评估LLM对非字面意图的理解能力。 |
large language model chain-of-thought |
|
|
| 9 |
Challenges and Opportunities in Text Generation Explainability |
剖析文本生成可解释性挑战与机遇,为开发更可靠的xAI方法提供指导 |
large language model |
|
|
| 10 |
Is Your LLM Outdated? A Deep Look at Temporal Generalization |
提出FreshBench评估框架,揭示大语言模型在时序泛化能力上的偏差与退化 |
large language model |
✅ |
|
| 11 |
ALMol: Aligned Language-Molecule Translation LLMs through Offline Preference Contrastive Optimisation |
ALMol:通过离线偏好对比优化对齐语言-分子翻译的大语言模型 |
large language model |
|
|
| 12 |
Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure |
利用LLM解释民事诉讼,提出基于人类分析的知识蒸馏与数据增强方法 |
large language model |
|
|