cs.CL（2025-12-22）

📊 共 30 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA 提出Moxin系列多模态开源模型，赋能视觉-语言-动作任务。 vision-language-action VLA large language model
2 How well do Large Language Models Recognize Instructional Moves? Establishing Baselines for Foundation Models in Educational Discourse 评估大型语言模型在教育场景中识别教学行为的能力，并建立基线。 large language model foundation model
3 HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Data 提出HARMON-E，利用层级Agentic推理从多模态肿瘤病历中抽取结构化数据 large language model multimodal
4 Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting 提出基于UMR的CoT提示方法，用于零样本ACSA任务，无需标注数据。 large language model chain-of-thought
5 Event Extraction in Large Language Model 综述基于大语言模型的事件抽取方法，并探讨其在构建可靠事件中心系统中的作用。 large language model multimodal
6 A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs 提出ROG框架，结合知识图谱检索与大语言模型推理解决复杂逻辑推理问题 large language model chain-of-thought
7 A Large-Language-Model Framework for Automated Humanitarian Situation Reporting 提出基于大语言模型的自动化人道主义情况报告框架，提升报告效率与质量。 large language model
8 HATS: High-Accuracy Triple-Set Watermarking for Large Language Models 提出高精度三集合水印方案HATS，用于保护大型语言模型生成文本的版权 large language model
9 ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models ChemATP：一种免训练的化学推理框架，用于增强大型语言模型 large language model
10 PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation PRISM：一个基于人格驱动的社交媒体模拟多智能体框架 large language model multimodal
11 SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation SiamGPT：面向稳定泰语文本生成的质量优先微调方法 large language model instruction following
12 PediaMind-R1: A Temperament-Aware Language Model for Personalized Early Childhood Care Reasoning via Cognitive Modeling and Preference Alignment PediaMind-R1：基于认知建模和偏好对齐的个性化育儿语言模型 large language model chain-of-thought
13 Auto-Prompting with Retrieval Guidance for Frame Detection in Logistics 提出检索引导的自动Prompt优化方法，用于提升物流文本中的框架检测精度。 large language model chain-of-thought
14 Context-Aware Initialization for Reducing Generative Path Length in Diffusion Language Models 提出上下文感知初始化方法，缩短扩散语言模型生成路径，加速推理。 large language model
15 Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning 提出InftyThink with Cross-Chain Memory，通过语义缓存提升LLM迭代推理能力 large language model
16 FASTRIC: Prompt Specification Language for Verifiable LLM Interactions FASTRIC：一种用于可验证LLM交互的提示规范语言 large language model
17 GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators GenEnv：通过LLM智能体与环境模拟器的难度对齐协同进化，提升智能体性能。 large language model
18 Exploring the features used for summary evaluation by Human and GPT 研究人类与GPT评估摘要时使用的特征，并提升GPT摘要评估能力 large language model
19 Increasing the Thinking Budget is Not All You Need 研究表明增加思考预算并非提升大语言模型推理能力的唯一途径 large language model
20 Epistemological Fault Lines Between Human and Artificial Intelligence 揭示人类与大型语言模型在认知上的根本差异，为AI治理提供理论基础 large language model
21 Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations 利用LLM激活值进行可泛化论文评分表征学习，提升跨prompt场景的评分能力 large language model
22 GuardEval: A Multi-Perspective Benchmark for Evaluating Safety, Fairness, and Robustness in LLM Moderators 提出GuardEval基准评测与GemmaGuard模型，提升LLM内容审核的安全性、公平性和鲁棒性 large language model
23 From Retrieval to Reasoning: A Framework for Cyber Threat Intelligence NER with Explicit and Adaptive Instructions 提出TTPrompt框架以解决网络威胁情报NER的指令适应性问题 large language model
24 CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs CienaLLM：利用自回归LLM从新闻文章中生成式提取气候影响信息 large language model
25 Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation 研究发现LLM对污名化群体的偏见与污名特征相关，并评估了安全模型缓解效果 large language model
26 Less is more: Not all samples are effective for evaluation 提出一种无需历史数据的测试集压缩框架，降低LLM评测成本并保持高保真度。 large language model
27 Stop saying LLM: Large Discourse Models (LDM) and Artificial Discursive Agent (ADA)? 提出以“大型话语模型(LDM)”和“人工话语代理(ADA)”替代“大型语言模型(LLM)”的分析框架。 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🔗⭐
28 AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards 提出AWPO，通过自适应融合推理奖励提升大语言模型工具使用能力 reinforcement learning large language model chain-of-thought
29 CodeSimpleQA: Scaling Factuality in Code Large Language Models CodeSimpleQA：提升代码大语言模型的事实性准确度 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
30 Gaming the Answer Matcher: Examining the Impact of Text Manipulation on Automated Judgment 研究文本操控对自动答案匹配的影响，发现其对简单攻击具有鲁棒性 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页