cs.CL（2025-08-20）

📊 共 30 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections 提出DocHop-QA以解决多文档多模态问答中的推理挑战 large language model multimodal
2 MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering 提出MedCoT-RAG以解决医疗问答中的推理不足问题 large language model chain-of-thought
3 Long Chain-of-Thought Reasoning Across Languages 研究多语言长链推理能力的迁移与提升 chain-of-thought
4 Credence Calibration Game? Calibrating Large Language Models through Structured Play 提出基于游戏结构的校准框架以提升大语言模型的信心估计 large language model
5 The Prompting Brain: Neurocognitive Markers of Expertise in Guiding Large Language Models 通过神经认知标记探索提示工程专家的脑功能连接 large language model
6 Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models 提出知识图谱注入微调方法以解决大语言模型推理不足问题 large language model
7 XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning 提出XFinBench以评估LLMs在复杂金融问题解决中的能力 large language model multimodal ✅
8 SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation 提出SignBind-LLM以解决手语翻译中的多模态融合问题 large language model
9 Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset 提出Nemotron-CC-Math以解决数学数据集质量不足问题 large language model
10 Trust but Verify! A Survey on Verification Design for Test-time Scaling 提出验证设计以优化测试时扩展性能 large language model ✅
11 Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs 系统研究后训练量化以优化扩散大语言模型的部署 large language model ✅
12 Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference 提出多语言自然语言推理框架以提升LLM的跨语言推理能力 large language model ✅
13 Transplant Then Regenerate: A New Paradigm for Text Data Augmentation 提出LMTransplant以解决文本数据增强的多样性问题 large language model
14 ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities 提出ZPD-SCA以解决LLMs评估学生认知能力的盲点问题 large language model
15 LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa 探讨大语言模型与代理AI在非洲保险决策中的应用与挑战 large language model
16 Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems 提出MultiCoXQL和Compass以解决多语言ConvXAI系统的数据稀缺问题 large language model
17 Scaled Signed Averaging Improves In-Context and Early Learning Benchmark Performance in Small Transformers 提出缩放签名平均法以解决小型变换器的学习限制问题 large language model
18 Counterspeech for Mitigating the Influence of Media Bias: Comparing Human and LLM-Generated Responses 提出反言论以缓解媒体偏见影响 large language model
19 QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning 提出基于RAG的LLM微调方法以解决伊斯兰继承推理问题 large language model
20 Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion 提出自我伪装攻击以解决AIGT检测规避问题 large language model
21 Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs 提出语义归一化框架以解决视觉叙事中的符号推理问题 multimodal
22 SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing 提出SurveyGen-I以解决科学调查生成中的一致性问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
23 TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting 提出TransLLM以解决城市交通多任务问题 reinforcement learning spatiotemporal large language model ✅
24 Improving LLMs for Machine Translation Using Synthetic Preference Data 通过合成偏好数据提升大型语言模型的机器翻译能力 DPO direct preference optimization large language model
25 Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning 提出基于四元数的姿态编码与对比学习以减少手语生成中的噪声 contrastive learning
26 NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model 提出Nemotron-Nano-9B-v2以提升推理任务的准确性与效率 Mamba
27 DEPTH: Hallucination-Free Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement 提出DEPTH框架以解决关系提取中的幻觉问题 reinforcement learning large language model
28 Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner 提出奖励转移的推测采样以提高测试时对齐效率 RLHF large language model
29 Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever 提出行为对齐检索器以减少不必要的API调用 contrastive learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
30 ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine 提出ShizhenGPT以解决中医领域多模态数据稀缺问题 PULSE large language model multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页