cs.CL（2025-09-10）

📊 共 21 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) (15) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications	研究表明医学大型语言模型存在显著记忆效应，可能影响其泛化性和安全性。	large language model
2	MultimodalHugs: Enabling Sign Language Processing in Hugging Face	提出MultimodalHugs以解决手语处理的灵活性问题	multimodal
3	Acquiescence Bias in Large Language Models	揭示大语言模型中的“否认偏见”：与人类的从众心理相反	large language model
4	DiTTO-LLM: Framework for Discovering Topic-based Technology Opportunities via Large Language Model	DiTTO-LLM：利用大语言模型发现基于主题的技术机会框架	large language model
5	ALIGNS: Unlocking nomological networks in psychological measurement through a large language model	ALIGNS：利用大型语言模型解锁心理测量中的语义网络，提升效度验证。	large language model
6	A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMs	提出基于角色感知的多智能体框架，提升LLM在金融教育问答中的准确性。	large language model chain-of-thought
7	Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation	提出SPICE指标，通过意愿调查评估LLM在不同语境下的交互倾向和持续参与度	large language model
8	Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings	提出一种基于心理测量学的文本数据分析方法，利用上下文嵌入揭示文本中的潜在知识维度。	large language model
9	Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora	提出葡萄牙语LLM高质量数据集构建方法，性能媲美工业级语料库	large language model
10	Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals	提出基于一致性信号的Agentic标注评估方法，无需人工反馈评估LLM标注质量。	large language model
11	The meaning of prompts and the prompts of meaning: Semiotic reflections and modelling	基于Peirce符号学理论，将LLM提示工程重构为动态符号互动过程	large language model
12	Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation	评估并缓解LLM在决策和摘要任务中的跨语言偏见，关注背景、性别和年龄的影响。	large language model
13	Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning	提出AncientDoc基准测试，评估视觉语言模型在古籍文档理解中的能力。	large language model
14	Too Helpful, Too Harmless, Too Honest or Just Right?	TrinityX：提出一种基于校准专家混合的模块化对齐框架，提升LLM的HHH对齐效果。	large language model
15	<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs	研究表明LLM生成的有毒文本在文本解毒任务中表现不如人工数据	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	🔗	⭐
16	CM-Align: Consistency-based Multilingual Alignment for Large Language Models	CM-Align：基于一致性的多语言对齐方法，提升大语言模型的多语言性能	DPO direct preference optimization large language model
17	Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M	SFT与DPO结合提升LLM安全性与有用性：OPT-350M实证研究	RLHF DPO direct preference optimization
18	A Survey of Reinforcement Learning for Large Reasoning Models	综述：强化学习驱动的大型推理模型研究进展	reinforcement learning large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation	量化LLM文本标注的潜在风险：揭示LLM破解现象及其对社会科学研究的影响	manipulation large language model
20	Adversarial Attacks Against Automated Fact-Checking: A Survey	综述性研究：针对自动化事实核查系统的对抗攻击方法	manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
21	CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework	提出CommonVoice-SpeechRE数据集与RPG-MoGe框架，提升语音关系抽取性能。	MoGe	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页