cs.CL（2026-06-30）

📊 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) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian	提出跨语言关系抽取方法以解决罗马尼亚低资源语言问题	large language model
2	Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law	提出PSALM框架以解决欧盟版权侵权评估问题	large language model
3	Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings	提出双嵌入水印技术以增强大语言模型的鲁棒性	large language model
4	Building a Multimodal Dataset of Academic Paper for Keyword Extraction	构建多模态学术论文数据集以提升关键词提取性能	multimodal
5	DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching	提出DigitalCoach以解决人机协作中的教学不足问题	multimodal visual grounding
6	LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment	提出LOPA以增强口语语言评估中的序数结构建模	large language model multimodal
7	Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?	提出MoralAltDataset以解决LLMs道德选择中的二元困境问题	large language model
8	When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors	提出数据引用批评机制以减少大型语言模型的引用错误	large language model
9	CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield	提出CHERRY以提高语言模型训练的计算效率	foundation model
10	Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics	提出基于LLM的管道以支持心理健康分析	large language model
11	Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG	提出Fair-GCG以解决推理中的歧视性刻板印象问题	large language model
12	Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues	提出Cue Visibility Gap以解决LLMs道德安全性评估问题	large language model
13	When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue	提出轻量级提示方法以解决任务导向对话中的数据库失败问题	large language model
14	SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference	提出SeKV以解决长上下文LLM推理中的KV缓存瓶颈问题	large language model	✅
15	Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies	提出LoFa基准以评估LLM对逻辑谬误的鲁棒性	large language model
16	CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations	提出CORTEX以解决RAG中的token级幻觉检测问题	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	🔗	⭐
17	Scalable Behaviour Cloning on Browser Using via Skill Distillation	通过技能蒸馏提出可扩展的浏览器行为克隆方法	behavior cloning distillation
18	Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs	提出元认知反馈强化学习以解决LLM不确定性表达问题	reinforcement learning
19	BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding	提出BlockPilot以优化扩散基础的推测解码策略	policy learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue	提出视觉语言模型以解决对称对话中的共享理解问题	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页