cs.CL（2026-01-19）

📊 共 31 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) (27 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models 提出循环置信链，解决大语言模型中时序感知的不确定性量化问题 large language model chain-of-thought
2 PhysicsSolutionAgent: Towards Multimodal Explanations for Numerical Physics Problem Solving 提出PhysicsSolutionAgent，生成带Manim动画的物理问题讲解视频 large language model multimodal
3 Trust Me, I'm an Expert: Decoding and Steering Authority Bias in Large Language Models 揭示并调控大语言模型中的权威偏见，提升推理任务的可靠性 large language model
4 Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning 利用时序逻辑校准LLM推理置信度，提升复杂任务表现 large language model
5 Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models 重新审视分词器：大型语言模型中的核心设计决策 large language model
6 A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits 首个组件级综述：探索大语言模型与多臂老虎机双向交互 large language model ✅
7 Race, Ethnicity and Their Implication on Bias in Large Language Models 通过可解释性分析揭示大语言模型中种族和族裔偏见的内在机制 large language model
8 Structured Insight from Unstructured Data: Large Language Models for SDOH-Driven Diabetes Risk Prediction 利用大语言模型从非结构化SDOH数据中提取信息，用于糖尿病风险预测 large language model
9 Adversarial Alignment: Ensuring Value Consistency in Large Language Models for Sensitive Domains 提出对抗对齐框架，提升大语言模型在敏感领域的价值观一致性 large language model
10 Multimodal Multi-Agent Empowered Legal Judgment Prediction 提出JurisMMA框架，通过多智能体协作解决法律判决预测中的多模态复杂推理问题 multimodal
11 Who Does This Name Remind You of? Nationality Prediction via Large Language Model Associative Memory 提出LAMA：利用大语言模型联想记忆进行国籍预测 large language model
12 Beyond Memorization: Testing LLM Reasoning on Unseen Theory of Computation Tasks 提出DFA构造基准测试，揭示LLM在形式语言推理中泛化能力不足 large language model chain-of-thought
13 Intelligent Documentation in Medical Education: Can AI Replace Manual Case Logging? 利用大型语言模型自动生成放射学病例记录，减轻医生负担并提高一致性 large language model chain-of-thought
14 Unlearning in LLMs: Methods, Evaluation, and Open Challenges 综述LLM中的Unlearning方法：分类、评估与挑战 large language model multimodal
15 Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses 提出CEDAR基准，评估LLM在文化引发的情感反应上的理解能力，揭示语言一致性与文化对齐的差异。 large language model multimodal
16 ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation ChartAttack：提出针对LLM图表生成恶意提示的评估框架，揭示其脆弱性 large language model multimodal
17 Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference 提出SPTS框架，通过自预测token跳过加速长文本LLM推理。 large language model
18 VISPA: Pluralistic Alignment via Automatic Value Selection and Activation VISPA：通过自动价值选择和激活实现大语言模型的多元化对齐 large language model
19 LLM-as-RNN: A Recurrent Language Model for Memory Updates and Sequence Prediction LLM-as-RNN：利用语言记忆更新的循环语言模型，提升序列预测能力 large language model
20 From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation 提出FusionRAG，通过融合检索增强生成中的上下文信息加速LLM推理。 large language model
21 A Shared Geometry of Difficulty in Multilingual Language Models 揭示多语言模型中难度几何：浅层泛化，深层特化 large language model
22 From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning 提出Search-and-Replace Infilling框架，解决代码补全中上下文错误修正难题。 instruction following
23 Leveraging Lora Fine-Tuning and Knowledge Bases for Construction Identification 利用LoRA微调和知识库识别英语双宾语结构 large language model
24 The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check 扩散语言模型在Agent任务中表现不佳，需引入因果推理机制 large language model
25 Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs 提出 IndoSoSci 数据集，并结合 RAG 方法提升 LLM 对印度尼西亚文化的理解 large language model
26 Rapport du Projet de Recherche TRAIMA TRAIMA项目：探索多模态交互在教育场景中的自动处理方法 multimodal
27 Towards Robust Process Reward Modeling via Noise-aware Learning 提出噪声感知学习框架，提升过程奖励模型在复杂推理中的鲁棒性 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🔗⭐
28 Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models 提出图推理范式GRP，结合拓扑感知强化学习，提升大语言模型结构化推理能力。 reinforcement learning large language model chain-of-thought
29 Aligning Agentic World Models via Knowledgeable Experience Learning 提出WorldMind框架，通过知识经验学习对齐Agentic世界模型 world model large language model
30 Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning 提出基于强化学习的Agentic对话搜索模型，通过上下文推理解决多轮对话中的信息检索与生成问题。 reinforcement learning large language model
31 SASA: Semantic-Aware Contrastive Learning Framework with Separated Attention for Triple Classification 提出SASA框架，通过分离注意力机制和语义感知对比学习增强三元组分类。 representation learning contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页