cs.CL（2025-08-15）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models 提出动态边界自我意识框架以提升大语言模型推理效率 large language model chain-of-thought
2 Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models 评估大型语言模型中的物种歧视问题 large language model
3 AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models' Responses to Depression, Anxiety, and Stress Queries 研究大型语言模型在心理健康领域的情感分析 large language model
4 LETToT: Label-Free Evaluation of Large Language Models On Tourism Using Expert Tree-of-Thought 提出LETToT框架以解决旅游领域LLM评估问题 large language model
5 Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText 提出集成方法以检测和缓解科学文本简化中的幻觉问题 large language model
6 LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText 提出基于LLM的科学文本简化方法以解决复杂性问题 large language model
7 A Multi-Task Evaluation of LLMs' Processing of Academic Text Input 评估大型语言模型在学术文本处理中的多任务能力 large language model
8 Can we Evaluate RAGs with Synthetic Data? 探讨合成数据在RAG评估中的有效性 large language model
9 Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse 提出在线反性别言论识别方法以应对政治话语中的性别偏见问题 large language model
10 Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions 通过问卷调查调整大型语言模型的人类价值观 large language model
11 When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs 提出五种方法以提升大语言模型的提示鲁棒性 large language model ✅
12 Feedback Indicators: The Alignment between Llama and a Teacher in Language Learning 提出基于Llama的反馈指标提取方法以优化语言学习反馈 large language model
13 SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral Analysis 提出SpecDetect以解决LLM生成文本检测问题 large language model
14 SGSimEval: A Comprehensive Multifaceted and Similarity-Enhanced Benchmark for Automatic Survey Generation Systems 提出SGSimEval以解决自动调查生成系统评估不足的问题 large language model
15 ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection 提出ToxiFrench以解决法语毒性检测问题 chain-of-thought
16 UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs? 揭示语言学奥林匹克难题对大型语言模型的挑战 large language model
17 E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection 提出E-CaTCH以解决社交媒体上的多模态虚假信息检测问题 multimodal

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

#题目一句话要点标签🔗⭐
18 From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System 提出多阶段对齐框架以解决生成查询建议中的用户偏好问题 reinforcement learning distillation large language model
19 Limitation Learning: Catching Adverse Dialog with GAIL 提出模仿学习方法以识别对话模型的局限性 imitation learning
20 CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity 提出CoDiEmb以解决信息检索与语义文本相似性联合学习中的负迁移问题 representation learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
21 HumorPlanSearch: Structured Planning and HuCoT for Contextual AI Humor 提出HumorPlanSearch以解决自动化幽默生成的上下文缺失问题 HuMoR large language model chain-of-thought
22 Detecting Hope, Hate, and Emotion in Arabic Textual Speech and Multi-modal Memes Using Large Language Models 利用大型语言模型检测阿拉伯文本中的希望、仇恨与情感 HuMoR large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页