cs.CL（2026-08-11）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Attention-Path Fragility as an Uncertainty Signal in Large Language Models	提出ASMI以解决大语言模型的不确定性问题	large language model
2	FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation	提出FaithformBench以评估数学链式推理自动形式化的可信度	chain-of-thought
3	SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information	提出SPIEval基准以评估大语言模型在移动助手中的表现	large language model	✅
4	From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models	提出MPAR-Bench以评估大语言模型的多点关联推理能力	large language model
5	VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?	提出VisEditBench以解决多模态反馈下可视化代码编辑问题	multimodal	✅
6	ReLTEx: Reliable LLM-based Taxonomy Expansion	提出ReLTEx框架以解决LLM生成分类法扩展的可靠性问题	large language model
7	VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?	提出VibeLifeBench以评估生活助手的主动性与持续性	large language model
8	The Illusion of Cross-Lingual Safety in Low-Resource Languages	提出LoDNA数据集以解决低资源语言的跨语言安全问题	large language model
9	TEAMMix: Taxonomy Enrichment Augmentation and Minority-augmented Mixing Strategy for LLM-enhanced Weak-Supervised Hierarchical Text Classification	提出TEAMMix以解决层次文本分类中的标签不平衡问题	large language model
10	Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching	提出自知识检索增强生成框架以解决专利匹配问题	large language model
11	Mitigating Context Interference for Reliable and Efficient Search Agents	提出基于蒸馏的上下文精炼方法以解决多轮搜索代理的干扰问题	large language model
12	EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection	提出EVIL-Detect以解决LLM生成文本检测问题	large language model	✅
13	Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases	提出精确Likert量表分布以评估LLM的态度与偏见	large language model
14	Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection	提出CalibDCD以解决大语言模型数据污染检测中的特征偏移问题	large language model
15	VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation	提出VoxSumm以解决长语音内容的摘要与翻译问题	instruction following

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation	提出无参考后训练方法以提升多语言机器翻译质量	reinforcement learning distillation large language model
17	DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation	提出DistilVDR以解决视觉文档检索中的模型庞大问题	distillation	✅
18	Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue	提出双环自演进框架以解决多轮同理对话中的情感反馈问题	reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Data Attribution of Emergent Misalignment with Persona Features	提出数据归因方法以解决语言模型的紧急失调问题	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页