cs.CL（2025-08-17）

📊 共 17 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) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Mitigating Hallucinations in Large Language Models via Causal Reasoning 提出CDCR-SFT以解决大语言模型的幻觉问题 large language model chain-of-thought ✅
2 MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph 提出MedKGent框架以构建动态演变的医学知识图谱 large language model TAMP
3 The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping 探讨大型语言模型中的句法引导对动词意义学习的影响 large language model
4 Uncovering Emergent Physics Representations Learned In-Context by Large Language Models 探讨大型语言模型在上下文中学习物理表征的能力 large language model
5 The Cultural Gene of Large Language Models: A Study on the Impact of Cross-Corpus Training on Model Values and Biases 提出文化基因概念以探讨大语言模型的文化偏见问题 large language model
6 What do Speech Foundation Models Learn? Analysis and Applications 提出轻量级分析框架以提升语音基础模型的理解与应用 foundation model
7 Arabic Multimodal Machine Learning: Datasets, Applications, Approaches, and Challenges 提出阿拉伯多模态机器学习的分类体系以解决研究空白问题 multimodal
8 Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow 提出认知决策路由框架以优化大语言模型的推理策略 large language model
9 Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models 评估OpenAI的GPT-OSS模型在多任务中的表现 large language model ✅
10 An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastive Semantic Highlighting and LLM Judgment 提出模糊全文本筛选管道以解决系统评价中的文献筛选问题 large language model
11 ZigzagAttention: Efficient Long-Context Inference with Exclusive Retrieval and Streaming Heads 提出ZigzagAttention以解决长上下文推理中的KV缓存问题 large language model
12 Research on intelligent generation of structural demolition suggestions based on multi-model collaboration 提出基于多模型协作的智能结构拆除建议生成方法 large language model
13 The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-Execution 提出自执行基准以评估大语言模型的自我预测能力 large language model
14 Fast, Slow, and Tool-augmented Thinking for LLMs: A Review 提出新分类法以提升大语言模型的推理能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
15 M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction Following 提出M3PO以解决LVLM偏好优化问题 RLHF DPO direct preference optimization
16 Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain 提出Legal$Δ$以解决法律推理模型的可靠性与可解释性问题 reinforcement learning large language model chain-of-thought ✅
17 ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models 提出ReaLM框架以增强小型语言模型的自主推理能力 reinforcement learning distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页