cs.CL（2024-12-22）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models	大型语言模型在说服和欺骗方面的能力分析与风险评估	large language model multimodal
2	Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models	提出激活边界防御(ABD)以抵御大语言模型中的越狱攻击	large language model
3	Robustness of Large Language Models Against Adversarial Attacks	评估GPT系列LLM在对抗攻击下的鲁棒性，揭示其脆弱性并强调改进需求	large language model
4	A Career Interview Dialogue System using Large Language Model-based Dynamic Slot Generation	提出基于LLM动态槽生成的职业访谈对话系统，提升访谈效率和质量。	large language model
5	Rationale-guided Prompting for Knowledge-based Visual Question Answering	提出基于推理引导的提示学习框架PLRH，提升知识型视觉问答性能	large language model chain-of-thought
6	SAIL: Sample-Centric In-Context Learning for Document Information Extraction	提出SAIL：一种面向文档信息抽取的样本中心化上下文学习方法	large language model
7	The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States	提出HalluRAG数据集，利用LLM内部状态检测RAG应用中的闭域幻觉	large language model
8	Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework	提出Aristotle框架，通过逻辑完备的分解-搜索-解决流程提升LLM的逻辑推理能力	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	🔗	⭐
9	Teaching LLMs to Refine with Tools	提出CaP方法，利用外部工具优化LLM的CoT推理，实现跨推理方式的有效改进。	DPO large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页