cs.CL（2026-02-17）

📊 共 18 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) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution	ViTaB-A：评估多模态大语言模型在视觉表格归因任务上的性能	large language model multimodal
2	ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models	ChartEditBench：评估多模态语言模型中基于视觉的交互式图表编辑能力	large language model multimodal
3	TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models	TAROT：面向代码生成，提出测试驱动和能力自适应的课程强化微调方法	large language model	✅
4	A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models	提出基于内容的网络安全拒绝决策框架，提升LLM防御能力。	large language model
5	Revisiting Northrop Frye's Four Myths Theory with Large Language Models	利用大型语言模型重探诺斯罗普·弗莱的四种神话原型理论	large language model
6	Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language	通过结构化提示，使大语言模型能够使用极低资源语言Tulu进行对话。	large language model
7	Extracting Consumer Insight from Text: A Large Language Model Approach to Emotion and Evaluation Measurement	提出LX模型，用于从文本中精准提取消费者情感与评价指标，提升营销研究效率。	large language model
8	Under-resourced studies of under-resourced languages: lemmatization and POS-tagging with LLM annotators for historical Armenian, Georgian, Greek and Syriac	利用大型语言模型标注器，研究低资源语言的词形还原和词性标注	large language model foundation model
9	Causal Effect Estimation with Latent Textual Treatments	提出基于稀疏自编码器和残差化的因果文本干预效果估计流水线	large language model
10	DependencyAI: Detecting AI Generated Text through Dependency Parsing	DependencyAI：利用依存句法分析检测AI生成文本，无需神经网络。	large language model
11	Fine-Refine: Iterative Fine-grained Refinement for Mitigating Dialogue Hallucination	提出Fine-Refine框架，通过细粒度迭代修正缓解对话系统中的幻觉问题	large language model
12	In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations	揭示LLM Agent潜在来源偏好：信息来源影响LLM生成内容	large language model
13	Measuring Social Integration Through Participation: Categorizing Organizations and Leisure Activities in the Displaced Karelians Interview Archive using LLMs	利用LLM对卡累利阿流离失所者访谈档案中的组织和休闲活动进行分类，以衡量社会融合度	large language model
14	Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory	提出Mnemis框架以解决长时记忆检索中的全局推理问题	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	🔗	⭐
15	STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens	STAPO：通过抑制罕见虚假token稳定LLM强化学习	reinforcement learning large language model
16	The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems	提出Vision Wormhole，实现异构多智能体系统中的无文本隐空间通信。	teacher-student distillation large language model	✅
17	jina-embeddings-v5-text: Task-Targeted Embedding Distillation	提出任务导向的蒸馏方法，用于训练高性能小型文本嵌入模型	distillation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos	提出FineMuSe数据集，用于社交媒体视频中细粒度性别歧视检测，并评估大型语言模型性能。	HuMoR multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页