cs.CL（2026-06-22）

📊 共 24 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models	提出PIVOTS基准以评估多模态大语言模型的人际关系推理能力	large language model multimodal	✅
2	Who Owns the AI Recommendation? A Multi-Industry Empirical Map of Brand Category Ownership Across Large Language Models	提出三项指标以分析AI推荐中的品牌所有权问题	large language model
3	TriggerBench: Investigating Prospective Memory for Large Language Models	提出TriggerBench以评估大语言模型的前瞻性记忆能力	large language model	✅
4	Same question, different history: language, national identity, and credit in large language models	分析语言对历史认知的影响，揭示大语言模型的文化记忆机制	large language model
5	Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models	提出实体级成员推断方法以解决LLM隐私泄露问题	large language model
6	Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews	研究语言特定情感极性偏差以提升产品评论分类准确性	large language model
7	WaveDetect: Robust Framework for Machine-Generated Text Detection via Wavelet Transform	提出WaveDetect以解决机器生成文本检测的鲁棒性问题	large language model foundation model
8	IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages	提出IndicGuard以解决印度语言安全性问题	large language model
9	War in the Abstract: The Rise and Consequences of Militarized Language in Scientific Communication	量化科学交流中军事化语言的影响及其后果	large language model
10	ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models	提出ReasoningLens以解决大型推理模型透明性问题	chain-of-thought
11	When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis	提出任务敏感的自我修正策略以提升语言模型表现	large language model
12	StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs	提出StatABench以系统评估LLMs的统计分析能力	large language model
13	AI Fiction in the Wild	探讨AI如何重塑小说创作与消费的关系	large language model
14	Randomized YaRN Improves Length Generalization for Long-Context Reasoning	提出随机化YaRN以改善长上下文推理的长度泛化问题	large language model
15	Uncertainty-based Debiasing and Unlearning for Decontamination	提出基于不确定性的去偏差与去学习方法以解决数据污染问题	large language model
16	Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs	提出RootMem以解决个性化LLMs的隐式逻辑记忆检索问题	large language model
17	Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis	提出KDoS框架以优化大语言模型的知识注入	large language model
18	The Language Blind Spot: How Query Language and Brand Recognition Tier Shape AI-Constructed Brand Reputation Across Twelve European Languages	提出多语言嵌入以解决品牌声誉监测中的语言盲点问题	large language model
19	A Dual-Track Framework for Template-Constrained LaTeX Conversion	提出双轨框架以解决LaTeX模板约束转换问题	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	🔗	⭐
20	PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation	提出PRIDE以解决同理心对话生成中的知识蒸馏问题	distillation privileged information large language model
21	Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails	提出后训练阶段知识蒸馏策略以提升小模型性能	distillation large language model instruction following
22	Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment	提出谓词重要性估计与解耦推理分数蒸馏以解决实体对齐问题	distillation large language model
23	Can LLMs Reliably Self-Report Adversarial Prefills, and How?	探讨LLMs在安全上下文中自我报告对抗性预填的可靠性	DPO large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Cross-National Information Attacks: A Two-Decade Analysis of Troll Behavior in Korea	提出可解释机器学习框架以检测韩国网络评论中的操控行为	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页