cs.CL（2024-12-05）

📊 共 20 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) (18) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Understanding Hidden Computations in Chain-of-Thought Reasoning	探索思维链推理中隐藏的计算过程，揭示Transformer模型的内部机制	large language model chain-of-thought
2	Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models	Quasar-1：提出温度引导推理，提升大语言模型逻辑推理能力	large language model chain-of-thought
3	M$^{3}$D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction	构建多模态、多语言、多任务数据集M³D，用于文档级信息抽取并提出分层多模态IE模型。	multimodal visual grounding
4	A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios	综述：基于大语言模型的社会智能体在博弈论场景中的应用研究	large language model
5	Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models	提出均匀离散积分梯度(UDIG)，有效解释大型语言模型	large language model
6	Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models	提出基于Agent AI和LangGraph的模块化框架，提升机器翻译质量与自动化水平	large language model
7	How Large Language Models (LLMs) Extrapolate: From Guided Missiles to Guided Prompts	将LLM视为外推机：揭示其成功与幻觉的深层原因	large language model
8	Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs	提出LIIPA框架，利用LLM揭示小说中隐式的人物刻画，提升分析准确性和公平性。	large language model chain-of-thought
9	MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM	提出MTMT，通过整合多重思维模式构建思维树，增强LLM的复杂推理能力	large language model chain-of-thought
10	Evolutionary Pre-Prompt Optimization for Mathematical Reasoning	提出EPPO：利用进化算法优化数学推理的预提示，显著提升LLM性能	large language model chain-of-thought
11	If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs	通过优化大规模模型融合，缓解性能权衡问题，有效利用次优模型检查点。	instruction following
12	Beyond the Binary: Capturing Diverse Preferences With Reward Regularization	提出基于奖励正则化的方法，以捕捉大语言模型中多样化的用户偏好	large language model
13	Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction	Aguvis：用于自主GUI交互的统一纯视觉智能体	multimodal
14	Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic	提出Arabic Stable LM 1.6B，一个面向阿拉伯语的小型但强大的语言模型。	large language model
15	A Context-aware Framework for Translation-mediated Conversations	提出TowerChat框架，通过上下文感知提升翻译对话系统性能	large language model
16	AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic	AL-QASIDA框架系统评估LLM在方言阿拉伯语中的质量和准确性	large language model
17	Reducing Tool Hallucination via Reliability Alignment	提出Relign框架，通过可靠性对齐减少LLM工具幻觉问题	large language model
18	Hostility Detection in UK Politics: A Dataset on Online Abuse Targeting MPs	构建针对英国议员的在线恶意言论数据集，用于政治语境下的敌意检测。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Reinforcement Learning Enhanced LLMs: A Survey	综述：强化学习赋能的大语言模型研究进展与挑战	reinforcement learning RLHF DPO	✅
20	ALMA: Alignment with Minimal Annotation	ALMA：通过最少标注实现大语言模型的有效对齐	distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页