cs.CL（2025-07-27）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Cognitive Chain-of-Thought: Structured Multimodal Reasoning about Social Situations 提出认知链式思考CoCoT，增强VLM在社会情境中的多模态推理能力 multimodal chain-of-thought
2 ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios 提出ELMES框架以解决教育场景中LLM评估问题 large language model ✅
3 Length Representations in Large Language Models 揭示大型语言模型中长度表征机制，通过调整注意力机制实现输出长度控制。 large language model
4 Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models 提出INT交互式叙事治疗师与IMA创新时刻评估，利用大语言模型改善心理健康支持。 large language model
5 CodeNER: Code Prompting for Named Entity Recognition CodeNER：利用代码提示提升大型语言模型在命名实体识别中的性能 large language model chain-of-thought
6 Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation 针对低资源场景，提出高效的方言阿拉伯语到现代标准阿拉伯语机器翻译方法 large language model chain-of-thought
7 MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning MoL-RL：通过将多步环境反馈提炼到LLM中，实现反馈独立的推理 large language model chain-of-thought
8 Goal Alignment in LLM-Based User Simulators for Conversational AI 提出UGST框架，提升LLM用户模拟器在对话AI中的目标一致性 large language model
9 AI-Driven Generation of Old English: A Framework for Low-Resource Languages 提出基于LLM的古英语生成框架，解决低资源语言的文化传承问题 large language model
10 RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing RMTBench：提出用户中心的多轮角色扮演评测基准，更贴近实际应用 large language model ✅
11 What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations 分析Aya-23内部语言表征，揭示多语言训练对LLM的影响 large language model
12 IQ Test for LLMs: An Evaluation Framework for Uncovering Core Skills in LLMs 提出基于因子分析的LLM评估框架，揭示模型潜在能力并辅助模型选择。 large language model
13 SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding 提出SessionIntentBench基准，用于电商用户行为理解中的会话意图建模 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
14 SGPO: Self-Generated Preference Optimization based on Self-Improver 提出SGPO：基于自提升器的自生成偏好优化，无需人工标注数据对齐LLM。 policy learning DPO direct preference optimization
15 Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering 提出Sem-DPO，通过语义一致性约束优化提示工程，提升文本到图像生成质量。 DPO direct preference optimization
16 Diversity-Enhanced Reasoning for Subjective Questions 提出MultiRole-R1框架，通过增强视角和token多样性提升主观问题推理能力。 reinforcement learning reward shaping chain-of-thought

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

#题目一句话要点标签🔗⭐
17 Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG 提出多阶段验证中心框架，缓解多模态RAG中的幻觉问题 egocentric ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页