cs.CL（2026-07-23）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education	提出MedGame框架以提升医学教育中的故事化学习体验	large language model multimodal
2	REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning	提出REFACT以解决长文本推理中的证据不足问题	large language model chain-of-thought	✅
3	Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models	提出机制以早期检测链式思维模型的推理非收敛问题	chain-of-thought
4	Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept	提出一种方法以追踪大型语言模型中的生动性概念	large language model
5	Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad	提出化学链式思维函数以解决分子推理中的幻觉问题	chain-of-thought
6	An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations	提出多轴评估框架以解决音频描述评估挑战	large language model multimodal
7	Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs	提出自适应深度稀疏框架以降低预训练大语言模型的推理成本	large language model
8	When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs	提出TriviaRoomQA基准以评估多语言LLM的日常知识表现	large language model
9	MemTools: A Unified Research Framework for Interoperable Agent Memory	提出MemTools框架以解决智能体记忆系统的互操作性问题	multimodal
10	Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable	提出CM-LRS以解决资本市场文档可银行性问题	large language model
11	news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling	提出news-crawler-LM以解决新闻页面内容提取问题	large language model
12	A Unified Moral-Value Dataset for Instruction Tuning	构建统一道德价值数据集以解决指令调优问题	large language model	✅
13	QuantiBias: Benchmarking Quantization-Induced Bias in LLMs	提出QuantiBias基准以评估LLMs中的量化引起的偏见问题	large language model
14	Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development	提出Transformer辅助的LLM源代码摘要生成方法以提升软件安全性	large language model
15	Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms	提出Khondo基准以解决孟加拉文档包拆分问题	multimodal	✅
16	Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders	探讨Qwen2.5-7B模型中的哥伦比亚身份推断	large language model
17	Agentic Evaluation of Copyright Law Compliance	提出Copyright-Bench以评估LLM代理的版权合规性	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	🔗	⭐
18	Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it	提出Epanorthosis指数以解决大型语言模型的修辞过度问题	RLHF large language model
19	Sample-Efficient Learning from Agent Experience	提出经验蒸馏方法以提高代理学习的样本效率	reinforcement learning distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	PrefReward: Learning User Preference Matrix for Personalized Text Generation	提出PrefReward以解决个性化文本生成中的用户偏好建模问题	implicit representation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页