| 1 |
WisPerMed at "Discharge Me!": Advancing Text Generation in Healthcare with Large Language Models, Dynamic Expert Selection, and Priming Techniques on MIMIC-IV |
利用大语言模型、动态专家选择和Priming技术,在MIMIC-IV上实现医疗文本生成 |
large language model |
|
|
| 2 |
EnviroExam: Benchmarking Environmental Science Knowledge of Large Language Models |
EnviroExam:构建环境科学知识评测基准,评估大语言模型性能 |
large language model |
|
|
| 3 |
Large Language Models Lack Understanding of Character Composition of Words |
揭示大语言模型在单词字符组成理解上的不足 |
large language model |
|
|
| 4 |
MBIAS: Mitigating Bias in Large Language Models While Retaining Context |
MBIAS:在保留上下文的同时减轻大型语言模型中的偏见 |
large language model |
✅ |
|
| 5 |
MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing |
提出MemeMQA框架,通过基于推理的多模态问答解决Meme理解难题。 |
multimodal |
|
|
| 6 |
Automating PTSD Diagnostics in Clinical Interviews: Leveraging Large Language Models for Trauma Assessments |
利用大型语言模型自动诊断临床访谈中的创伤后应激障碍 |
large language model |
|
|
| 7 |
LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs |
提出基于伪标签不可回答问题的自训练方法,提升EHR文本到SQL系统的可靠性 |
large language model |
|
|
| 8 |
Cross-Language Assessment of Mathematical Capability of ChatGPT |
跨语言评估ChatGPT数学能力:聚焦印地语等区域语言 |
chain-of-thought |
|
|
| 9 |
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving |
MapCoder:多智能体协同代码生成,解决复杂编程问题 |
large language model |
✅ |
|