cs.CL（2024-05-05）

📊 共 11 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning	提出MedAdapter，用于医学推理中大语言模型的高效测试时自适应	large language model
2	Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning	MathTrap数据集揭示大语言模型在数学推理中组合泛化能力的不足	large language model
3	Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education	利用大型语言模型评估K-12教育中简答题的自动评分能力	large language model
4	Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive Study	评估大型语言模型在孟加拉语自然语言推理任务中的性能，揭示其优势与局限。	large language model
5	Relay Decoding: Concatenating Large Language Models for Machine Translation	提出Relay Decoding，通过拼接大语言模型实现机器翻译，无需昂贵的持续学习。	large language model
6	NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli	提出NegativePrompt，利用负面情绪刺激提升大语言模型性能	large language model	✅
7	Leveraging Lecture Content for Improved Feedback: Explorations with GPT-4 and Retrieval Augmented Generation	利用RAG增强GPT-4，改进编程学习反馈，提升教学效果	large language model TAMP
8	Self-Reflection in LLM Agents: Effects on Problem-Solving Performance	LLM自反思显著提升问题解决能力	large language model	✅
9	Language Evolution for Evading Social Media Regulation via LLM-based Multi-agent Simulation	提出基于LLM多智能体模拟的语言演化框架，用于研究社交媒体监管下的规避策略。	large language model
10	Labeling supervised fine-tuning data with the scaling law	提出一种基于Scaling Law校准的多阶段人工标注方法，用于低资源环境下高质量SFT数据获取。	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	🔗	⭐
11	A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU	提出预测感知对比学习框架PACL，解决多意图NLU中模型混淆问题。	contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页