cs.CL（2026-06-26）

📊 共 17 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) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 Dialogue to Detection: A Multimodal Hybrid NLP Pipeline for Insurance Fraud Detection 提出多模态混合NLP管道以解决保险欺诈检测问题 multimodal
2 From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models 提出基于探针的不确定性估计方法以解决大语言模型的幻觉检测问题 large language model ✅
3 Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models 提出因果机制分析以解决视觉-知识冲突问题 multimodal visual grounding
4 Do Speech Emphasis Models Generalize across Languages and Emotions? 提出MMEE语音强调模型以解决跨语言和情感的泛化问题 zero-shot transfer
5 Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs 提出三方狼人游戏以增强大型语言模型的多跳心智理论能力 large language model
6 Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study 提出基于输出空间分配成本的LLM压缩方法以提高模型精度 large language model
7 Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning 提出低亲和力人格条件化以解决安全性问题 large language model
8 Mitigating LLM-based p-Hacking by Preregistering for the Next LLM 提出预注册协议以解决LLM研究中的p-hacking问题 large language model
9 Mechanism-Driven Monitors for Preemptive Detection of LLM Training Instability 提出机制驱动监测以预防大型语言模型训练不稳定问题 large language model
10 Scaling limit of the Random Language Model 提出随机语言模型的定量理论以解决语言统计问题 large language model
11 A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs 提出树思维启发的混合方法以改善法律案例判决摘要 large language model
12 An Empirical Analysis of Factual Errors in Human-Written Text and its Application 提出人类文本事实错误检测方法以填补LLM研究空白 large language model
13 Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling 提出层特定位置嵌入缩放方法以解决长文本信息丢失问题 large language model
14 When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search 提出DiscoBench以解决模糊搜索请求的问题 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🔗⭐
15 From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond 将大型语言模型视为世界模型的特例，探讨其持续发展路径 world model world models JEPA
16 Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety 提出Yuvion LLM以解决内容与AI安全问题 reinforcement learning large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
17 Masked Language Flow Models 提出Masked Language Flow Models以解决多步骤推理问题 MDM instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页