cs.CL（2024-07-24）

📊 共 13 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	IgnitionInnovators at "Discharge Me!": Chain-of-Thought Instruction Finetuning Large Language Models for Discharge Summaries	利用思维链指令微调大型语言模型，IgnitionInnovators 解决出院总结生成任务	large language model chain-of-thought	✅
2	Boosting Large Language Models with Socratic Method for Conversational Mathematics Teaching	提出SocraticLLM以提升数学教学效果	large language model chain-of-thought	✅
3	SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)	SDoH-GPT：利用大语言模型提取社会健康决定因素，显著降低标注成本。	large language model
4	Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity Recognition	提出LAR方法，利用通用大语言模型解决跨领域命名实体识别中的标签冲突问题。	large language model
5	To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity	分析大语言模型在歧义下的自洽性，揭示其知识应用的不一致性。	large language model
6	Sentiment Reasoning for Healthcare	提出情感推理任务，增强AI医疗决策透明性，并构建多模态情感分析数据集。	large language model multimodal	✅
7	Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs	传统方法在信用评级预测中优于生成式LLM：数值与多模态数据编码是关键	large language model multimodal
8	CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models	提出CMR缩放定律，预测持续预训练中语言模型的关键混合比例，优化训练效率。	large language model
9	SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle	SimCT：LLM开发生命周期中一种简单的模型一致性测试协议	large language model
10	Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education	利用大型语言模型评估韩语学生写作，提升教育反馈质量	large language model
11	Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism	提出二维坐标系框架，系统性理解大语言模型上下文学习机制	large language model
12	Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning	提出Train-Attention机制，通过元学习动态调整token权重，提升LLM持续知识学习效率。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	SAFETY-J: Evaluating Safety with Critique	SAFETY-J：提出一种基于批判性评估的双语生成式安全评估器，提升内容安全评估的透明性和准确性。	preference learning large language model	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页