| 1 |
Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes |
结合CoT与RAG提升LLM在临床笔记中罕见病诊断的准确性 |
large language model foundation model chain-of-thought |
|
|
| 2 |
Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models |
分析大型视觉-语言模型对多模态讽刺的感知差异,揭示其主观性和不确定性。 |
multimodal |
✅ |
|
| 3 |
Large Language Models in Legislative Content Analysis: A Dataset from the Polish Parliament |
构建波兰议会立法内容分析数据集,探索LLM在法律领域的应用潜力。 |
large language model |
|
|
| 4 |
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models |
提出信息引导探针,用于识别专有大语言模型中的训练数据印记 |
large language model |
|
|
| 5 |
The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation |
发布Lucie-7B多语言大模型及训练数据集,着重解决现有模型中以英语为中心的偏见问题。 |
large language model foundation model |
|
|
| 6 |
Interpretation Gaps in LLM-Assisted Comprehension of Privacy Documents |
揭示LLM辅助理解隐私政策时存在的解释偏差问题 |
large language model |
|
|
| 7 |
RECSIP: REpeated Clustering of Scores Improving the Precision |
RECSIP:通过重复聚类评分提高大语言模型精度 |
large language model |
|
|
| 8 |
TLUE: A Tibetan Language Understanding Evaluation Benchmark |
提出TLUE:首个大规模藏语理解评估基准,用于评估LLM在藏语上的能力。 |
large language model |
|
|