cs.CL（2025-05-13）

📊 共 27 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 VLM-KG: Multimodal Radiology Knowledge Graph Generation 提出VLM-KG框架，首个用于生成多模态放射学知识图谱的方案。 multimodal instruction following
2 Large Language Models Meet Stance Detection: A Survey of Tasks, Methods, Applications, Challenges and Future Directions 综述：大型语言模型在立场检测中的应用、方法、挑战与未来方向 large language model multimodal
3 Accelerating Chain-of-Thought Reasoning: When Goal-Gradient Importance Meets Dynamic Skipping 提出Adaptive GoGI-Skip框架，通过动态跳过实现高效的CoT推理加速。 large language model chain-of-thought
4 ALOHA: Empowering Multilingual Agent for University Orientation with Hierarchical Retrieval ALOHA：一种基于分层检索的多语言智能体，用于增强大学迎新服务。 large language model Aloha
5 HealthBench: Evaluating Large Language Models Towards Improved Human Health HealthBench：用于评估大型语言模型在医疗健康领域的性能与安全性的基准测试。 large language model instruction following
6 Enhancing Thyroid Cytology Diagnosis with RAG-Optimized LLMs and Pa-thology Foundation Models 结合RAG优化LLM与病理学基础模型，提升甲状腺细胞学诊断水平 large language model foundation model
7 Aya Vision: Advancing the Frontier of Multilingual Multimodality Aya Vision：通过数据合成与模型融合，推进多语言多模态前沿 multimodal
8 LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Models 提出基于LLM的比较式论文评分方法LCES，实现零样本自动论文评分。 large language model
9 Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement 综述LLM心理测量学：利用心理测量学评估、验证和提升大语言模型 large language model ✅
10 HCR-Reasoner: Synergizing Large Language Models and Theory for Human-like Causal Reasoning HCR-Reasoner：融合大语言模型与因果理论，实现类人因果推理 large language model
11 Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies 揭示大语言模型概率一致性偏差：理论完备性与实证差异分析 large language model
12 NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context NurValues：构建临床情境下大型语言模型护理价值观对齐评估基准 large language model ✅
13 Small but Significant: On the Promise of Small Language Models for Accessible AIED 探索小型语言模型在可访问AI教育中的潜力，解决资源受限机构的AI工具可及性问题。 large language model
14 Enhancing Cache-Augmented Generation (CAG) with Adaptive Contextual Compression for Scalable Knowledge Integration 提出自适应上下文压缩的缓存增强生成框架，提升大规模知识集成效率 large language model
15 A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs 提出预训练不确定性量化头，用于检测LLM输出中的幻觉 large language model
16 A suite of LMs comprehend puzzle statements as well as humans 大型语言模型在理解谜题语句方面与人类表现相当甚至超越 large language model
17 Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation 提出ASEE框架，结合模式释义与检索增强生成，解决事件抽取中模式选择与幻觉问题。 large language model
18 Automatic Task Detection and Heterogeneous LLM Speculative Decoding 提出异构LLM推测解码方法，提升下游任务效率与加速LLM推理。 large language model
19 LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries LibVulnWatch：利用Agent深度评估开源AI库的潜在安全风险 large language model
20 IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation IterKey：利用LLM迭代生成关键词，增强检索增强生成效果 large language model
21 A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court 构建意大利最高法院判决主题建模数据集的文档处理流水线 large language model
22 TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers TUMS：利用多结构处理器增强LLM的工具使用能力 large language model
23 Towards Contamination Resistant Benchmarks 提出一种抗污染的LLM评测基准，解决现有评测的可靠性问题。 large language model
24 Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow 评估黑盒提示优化方法在大规模LLM上的有效性，发现其收益递减 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🔗⭐
25 Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage 提出融合双向思维链与奖励机制的方法，提升大语言模型在中文非遗问答中的能力。 distillation large language model
26 Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring 研究CEFR提示的大语言模型在西班牙语互动教学中存在的对齐漂移问题 teacher-student large language model
27 Detecting Prefix Bias in LLM-based Reward Models 提出检测LLM奖励模型中前缀偏差的方法，提升模型公平性 reinforcement learning RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页