cs.CL（2025-01-03）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Instruction-Following Pruning for Large Language Models	提出指令跟随剪枝，实现大语言模型基于指令的动态稀疏化	large language model instruction following
2	A Survey on Large Language Models with some Insights on their Capabilities and Limitations	综述大型语言模型能力与局限性，深入探讨CoT、PoT及外部系统集成。	large language model chain-of-thought
3	CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System	CarbonChat：基于大语言模型的企业碳排放分析与气候知识问答系统	large language model TAMP
4	Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations	提出FLLM：融合领域知识增强LLM在时尚推荐中的个性化能力	large language model
5	A non-ergodic framework for understanding emergent capabilities in Large Language Models	提出非遍历框架，解释大语言模型涌现能力，并指导架构设计	large language model
6	Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models	提出递归逻辑思维分解框架以提升大语言模型推理能力	large language model
7	AGGA: A Dataset of Academic Guidelines for Generative AI and Large Language Models	AGGA：一个用于生成式AI和大型语言模型学术指南的数据集	large language model
8	MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments	MIRAGE：构建复杂社交互动环境，评估大型语言模型在角色扮演中的能力	large language model	✅
9	Time Series Language Model for Descriptive Caption Generation	提出TSLM：一种用于时间序列描述性字幕生成的时间序列语言模型	large language model foundation model
10	An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage	揭示LLM在文化遗产文本生成中存在的价值偏差问题，并提出评估基准。	large language model
11	Automating Legal Interpretation with LLMs: Retrieval, Generation, and Evaluation	提出ATRIE框架，利用LLM自动进行法律概念解释，提升法律从业效率。	large language model
12	ICPC: In-context Prompt Compression with Faster Inference	提出ICPC，通过上下文提示压缩加速LLM推理，解决长提示输入难题。	large language model
13	Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions	提出POATE对比问答攻击方法，揭示并防御大语言模型推理漏洞	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	🔗	⭐
14	Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge Graphs	提出融合多模态对比学习的生物医学知识图谱嵌入方法，提升链接预测性能。	representation learning contrastive learning multimodal	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页