cs.CL（2026-09-02）

📊 共 22 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Do Large Language Models Capture the Diversity in their Training Data? 提出后处理机制以提高大语言模型的条件多样性 large language model
2 Predictors of Loneliness in Older Adults Using Multimodal Analysis of Speech and Language 提出多模态分析方法以识别老年人孤独感 multimodal
3 When Persona Attributes Improve Population Alignment in Large Language Models 提出个性化属性选择方法以提升大语言模型在人类响应预测中的表现 large language model
4 Debias-SparseGPT: Bias-Aware Pruning for Large Language Models 提出Debias-SparseGPT以解决大语言模型的偏见问题 large language model
5 A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models 提出三代理框架以评估和对齐大型语言模型的问题澄清能力 large language model
6 Language Models Can Control Their Own Attention 提出声明性注意力以优化语言模型的上下文处理 chain-of-thought
7 When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models 探讨语言模型中的逻辑有效性与行为表现的关系 large language model
8 DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models 提出DKL以解决指令调优语言模型知识注入问题 instruction following
9 text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation 提出text2ql以解决自然语言查询数据库的结构性限制 large language model
10 User Feedback Provides a Unique Signal that LLMs Can not Detect 提出用户反馈信号以提升大型语言模型的有效性 large language model
11 DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation 提出DiscoSign以解决手语翻译中的话语理解问题 large language model
12 How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling 分析LLMs如何构建虚构世界以提升叙事能力 large language model
13 SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval 提出SonicCaps以解决音频描述数据集多样性不足问题 large language model ✅
14 From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X 提出一种有效的愤怒诱导内容检测框架以应对在线情绪操控问题 large language model
15 A Layered Taxonomy for Chinese Learner Grammatical Error Annotation 提出分层分类法以解决中文学习者语法错误标注问题 large language model
16 AI agents reshape consensus formation in human groups 研究AI代理如何重塑人类群体中的共识形成 large language model
17 Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage 提出选择性知识编辑反转方法以解决安全风险问题 large language model
18 HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs 提出HyGRAIL以解决科学假设发现中的成本与证据问题 large language model
19 NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis 提出NS-Copilot以解决神经科学分析中的跨学科障碍问题 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🔗⭐
20 NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning 提出NE-R1框架以增强命名实体识别模型的性能 reinforcement learning large language model
21 RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution 提出RideSkill以解决复杂的共享出行问题 reinforcement learning large language model
22 IDEEA: training-free Input-Dependent stEEring via Activation cluster matching 提出IDEEA以解决输入依赖的模型引导问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页