cs.CL（2025-06-24）

📊 共 28 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) (24 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model 提出ECCoT框架以提升大语言模型的有效认知能力 large language model chain-of-thought ✅
2 Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models 利用大型语言模型进行对话系统的常识生成与评估 large language model chain-of-thought
3 A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models 提出详细因子分析方法以评估大型语言模型的政治偏见 large language model
4 Arabic Dialect Classification using RNNs, Transformers, and Large Language Models: A Comparative Analysis 提出基于RNN、Transformer和大语言模型的阿拉伯方言分类方法 large language model
5 Social Hatred: Efficient Multimodal Detection of Hatemongers 提出多模态方法以高效检测网络仇恨者 multimodal
6 AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models 提出AnTKV以解决大语言模型KV缓存量化精度下降问题 large language model
7 Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning 提出对话教学法以解决大语言模型教育应用中的不足问题 large language model
8 MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages 提出MuBench以评估多语言大模型的能力差异 large language model
9 Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs 提出Inference-Scaled GraphRAG以解决知识图谱多跳问答问题 large language model chain-of-thought
10 MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration 提出模块化多智能体框架以解决多模态医学诊断问题 large language model multimodal ✅
11 Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents 提出Doc2SAR以解决科学文献中结构-活性关系提取问题 large language model multimodal
12 LLM-Based Social Simulations Require a Boundary 提出明确边界以提升LLM社交模拟的可靠性 large language model
13 Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study 提出数据合成方法以提升开源LLM的数据分析能力 large language model ✅
14 Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains? 探讨强化后训练在新领域的迁移能力 large language model
15 PromptAug: Fine-grained Conflict Classification Using Data Augmentation 提出PromptAug以解决社交媒体冲突行为分类问题 large language model
16 Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge 提出自我纠正方法以解决新闻摘要中的虚假信息问题 large language model
17 KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs 提出KnowMap以解决大语言模型任务适应性不足问题 large language model
18 Automated Detection of Pre-training Text in Black-box LLMs 提出VeilProbe以解决黑箱LLM预训练文本检测问题 large language model
19 Measuring and Guiding Monosemanticity 提出特征单义性评分以解决特征表示操控问题 large language model
20 Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation 提出原子级评估框架以解决语言模型个性一致性问题 large language model
21 EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition 提出EmoStage框架以解决心理咨询中共情响应生成问题 large language model
22 What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning 探讨LLM生成数据的多样性对模型微调的影响 large language model
23 Hallucination Detection with Small Language Models 提出小型语言模型框架以检测大语言模型的幻觉问题 large language model
24 Augmenting Multi-Agent Communication with State Delta Trajectory 提出状态增量轨迹以增强多智能体通信 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
25 Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? 研究表明推理方法对大语言模型捕捉人类标注者分歧的影响 reinforcement learning RLHF large language model
26 CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation 提出CycleDistill以解决低资源语言机器翻译问题 distillation large language model
27 SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning 提出SRFT方法以优化大语言模型推理能力 reinforcement learning large language model
28 Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager 提出基于强化学习的对话管理器以实现个性化对话 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页