cs.CL（2026-02-13）

📊 共 18 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) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#	题目	一句话要点	标签	🔗	⭐
1	Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models	提出基于元认知的知识增强框架，提升大语言模型知识可靠性	large language model
2	Exploring a New Competency Modeling Process with Large Language Models	提出基于大语言模型的新型胜任力建模流程，提升人才管理的效率与客观性。	large language model
3	BaziQA-Benchmark: Evaluating Symbolic and Temporally Compositional Reasoning in Large Language Models	提出BaziQA-Benchmark，用于评估大语言模型在符号和时间组合推理方面的能力。	large language model
4	MentalBench: A Benchmark for Evaluating Psychiatric Diagnostic Capability of Large Language Models	MentalBench：用于评估大型语言模型精神疾病诊断能力的基准测试	large language model
5	Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens	提出基于深度思考Token的大语言模型推理努力度量方法，并优化推理效率。	large language model chain-of-thought
6	ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter	ReFilter：通过门控滤波器提升检索增强生成在知识密集型问答中的鲁棒性	large language model zero-shot transfer
7	RAT-Bench: A Comprehensive Benchmark for Text Anonymization	RAT-Bench：一个基于重识别风险的文本匿名化综合基准测试	large language model
8	Using Machine Learning to Enhance the Detection of Obfuscated Abusive Words in Swahili: A Focus on Child Safety	利用机器学习增强斯瓦希里语中混淆性辱骂词语的检测，关注儿童安全	multimodal
9	Semantic Chunking and the Entropy of Natural Language	提出基于语义分块的自然语言熵模型，解释语言冗余度并预测熵率。	large language model
10	Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence	LLM的语言能力与大脑活动预测的左右半球不对称性相关	large language model
11	SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs	SecureGate：通过令牌门控双适配器为联邦LLM学习安全地揭示PII	large language model
12	When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms	构建孟加拉语成语数据集，揭示LLM在低资源语言文化理解上的局限性	large language model
13	Learning Ordinal Probabilistic Reward from Preferences	提出概率奖励模型以解决现有奖励模型的局限性	large language model
14	CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation	提出CLASE混合方法，用于评估中文法律文本的文风质量。	large language model	✅
15	DiffuRank: Effective Document Reranking with Diffusion Language Models	提出DiffuRank，利用扩散语言模型进行高效文档重排序，克服自回归模型的局限性。	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	🔗	⭐
16	$\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models	提出$ ext{X}$-KD以解决大语言模型知识蒸馏中的环境忽视问题	reinforcement learning imitation learning inverse reinforcement learning
17	MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs	MedXIAOHE：构建医学多模态大模型，提升临床应用中的医学理解与推理能力	reinforcement learning foundation model multimodal
18	Doc-to-LoRA: Learning to Instantly Internalize Contexts	提出Doc-to-LoRA，通过元学习快速将上下文信息内化到LLM中，加速长文本处理。	distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页