cs.CL（2025-12-22）

📊 共 22 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19) 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) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting	提出基于UMR的CoT提示方法，探索零样本ACSA任务	large language model chain-of-thought
2	Event Extraction in Large Language Model	综述性论文：探讨大语言模型在事件抽取中的应用，并展望未来发展方向。	large language model multimodal
3	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，解决复杂逻辑推理难题。	large language model chain-of-thought
4	ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models	ChemATP：一种用于大语言模型的免训练化学推理框架	large language model
5	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
6	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
7	Auto-Prompting with Retrieval Guidance for Frame Detection in Logistics	提出检索引导的自动Prompt优化方法，提升LLM在物流文本框架检测中的性能。	large language model chain-of-thought
8	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
9	Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation	研究揭示LLM中针对污名化群体的偏见特征，并评估Guardrail模型缓解效果	large language model
10	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
11	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
12	Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations	利用LLM激活值进行可泛化Essay评分表征学习，提升跨Prompt场景性能	large language model
13	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
14	Increasing the Thinking Budget is Not All You Need	研究表明，单纯增加思考预算并非提升大语言模型推理能力的最佳途径	large language model
15	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
16	From Retrieval to Reasoning: A Framework for Cyber Threat Intelligence NER with Explicit and Adaptive Instructions	提出TTPrompt框架，通过显式指令提升网络威胁情报命名实体识别性能。	large language model
17	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
18	Stop saying LLM: Large Discourse Models (LDM) and Artificial Discursive Agent (ADA)?	提出用“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
19	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

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
20	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
21	AWPO: Enhancing Tool-Use of Large Language Models through Explicit Integration of Reasoning Rewards	提出AWPO，通过显式整合推理奖励增强大语言模型工具使用能力	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	🔗	⭐
22	MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments	MobileWorld：面向Agent-用户交互和MCP增强环境的移动Agent基准测试	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页