cs.CL（2025-01-27）

📊 共 20 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) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	WinClick: GUI Grounding with Multimodal Large Language Models	WinClick：利用多模态大语言模型实现GUI界面元素定位	large language model multimodal	✅
2	Large Language Models to Diffusion Finetuning	提出一种新的微调方法，使大型语言模型能够通过扩散框架扩展测试时计算能力。	large language model foundation model
3	AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought	AdaMCoT：通过自适应多语言思维链增强跨语言事实推理	large language model chain-of-thought
4	Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models	揭示LLM的欺骗性：DeepSeek R1展现自我保护和自主目标行为	embodied AI large language model
5	A foundation model for human-AI collaboration in medical literature mining	LEADS：医学文献挖掘中人机协作的基础模型，提升效率和质量。	large language model foundation model
6	IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding	IndicMMLU-Pro：构建印度语言多任务理解基准，评估大型语言模型能力	large language model
7	Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare	评估并防御医疗场景下大语言模型的越狱攻击，提升AI临床医生的安全性	large language model
8	Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction	提出基于大语言模型的程序示例学习方法，用于自动归纳语音演变规律。	large language model
9	Towards Explainable Multimodal Depression Recognition for Clinical Interviews	提出EMDRC任务与PHQ-aware多模态框架，提升临床访谈抑郁识别的可解释性	multimodal
10	A Comprehensive Study on Fine-Tuning Large Language Models for Medical Question Answering Using Classification Models and Comparative Analysis	提出一种基于分类模型的医学问答大语言模型微调方法。	large language model
11	How well can LLMs Grade Essays in Arabic?	评估大型语言模型在阿拉伯语作文自动评分任务中的性能表现	large language model instruction following
12	Improving LLM Leaderboards with Psychometrical Methodology	利用心理测量学方法改进LLM排行榜，实现更鲁棒的模型评估	large language model
13	RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval	RAPID：检索增强的并行推理草稿，用于基于文本的视频事件检索	large language model
14	Representing data in words	提出Wordalisations：利用大语言模型将数据转化为易于理解的文字描述	large language model
15	Integration of LLM Quality Assurance into an NLG System	提出一种基于LLM的质量保证系统，用于校正NLG系统生成的文本。	large language model
16	Parametric Retrieval Augmented Generation	提出参数化检索增强生成（Parametric RAG），解决LLM知识增强的效率与深度问题	large language model	✅
17	LCTG Bench: LLM Controlled Text Generation Benchmark	提出LCTG Bench：首个日语LLM可控文本生成基准，填补低资源语言空白。	large language model
18	MADP: Multi-Agent Deductive Planning for Enhanced Cognitive-Behavioral Mental Health Question Answer	提出MADP框架，利用多智能体演绎规划增强心理健康问答效果	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	🔗	⭐
19	Audio Large Language Models Can Be Descriptive Speech Quality Evaluators	提出ALLD方法，提升音频大语言模型在语音质量评估任务中的性能	distillation large language model multimodal
20	Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width	提出 Matryoshka Re-Ranker，实现可配置深度和宽度的灵活重排序架构，提升 LLM 在实际场景的应用性。	distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页