cs.CL（2025-08-08）

📊 共 30 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (25 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (25 篇)

#题目一句话要点标签🔗⭐
1 Confidence Estimation for Text-to-SQL in Large Language Models 提出文本到SQL的置信度估计方法以提升模型可靠性 large language model
2 Large Language Models for Oral History Understanding with Text Classification and Sentiment Analysis 提出可扩展框架以自动化日裔美国人监禁口述历史的情感与语义标注 large language model ✅
3 Measuring Stereotype and Deviation Biases in Large Language Models 研究大型语言模型中的刻板印象与偏差偏见 large language model
4 Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models 提出IAPO框架以优化黑箱大语言模型的提示与推理策略 large language model
5 Large Language Model Data Generation for Enhanced Intent Recognition in German Speech 提出结合生成模型以提升德语语音意图识别能力 large language model
6 Contrastive Analysis of Constituent Order Preferences Within Adverbial Roles in English and Chinese News: A Large-Language-Model-Driven Approach 基于大语言模型的英汉新闻副词角色成分顺序对比分析 large language model
7 EICAP: Deep Dive in Assessment and Enhancement of Large Language Models in Emotional Intelligence through Multi-Turn Conversations 提出EICAP以提升大语言模型的情感智能能力 large language model
8 DKG-LLM : A Framework for Medical Diagnosis and Personalized Treatment Recommendations via Dynamic Knowledge Graph and Large Language Model Integration 提出DKG-LLM框架以解决医疗诊断与个性化治疗推荐问题 large language model
9 Do Biased Models Have Biased Thoughts? 研究链式思维提示对语言模型偏见的影响 large language model chain-of-thought
10 T-REX: Table -- Refute or Entail eXplainer 提出T-REX以解决多模态表格数据的文本声明验证问题 large language model multimodal
11 LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data 提出LLMCARE以解决早期认知障碍检测问题 large language model multimodal
12 InfoCausalQA:Can Models Perform Non-explicit Causal Reasoning Based on Infographic? 提出InfoCausalQA以评估基于信息图的因果推理能力 multimodal visual grounding
13 Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge 提出统计方法以测量大型语言模型的自我偏见 large language model
14 BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent 提出BrowseComp-Plus以解决深度研究代理评估的公平性与透明性问题 large language model
15 SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning 提出SlimInfer以加速长上下文LLM推理 large language model ✅
16 Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages 提出轻量级LLM以跨语言分类移民话题 large language model
17 Memp: Exploring Agent Procedural Memory 提出Memp以解决代理程序记忆脆弱问题 large language model
18 Quantifying Conversation Drift in MCP via Latent Polytope 提出SecMCP以解决MCP中的对话漂移问题 large language model
19 LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing 提出ChatAnime数据集以解决LLMs情感支持角色扮演的研究空白 large language model ✅
20 Evaluating Style-Personalized Text Generation: Challenges and Directions 提出风格个性化文本生成评估方法以解决现有指标不足问题 large language model
21 PREF: Reference-Free Evaluation of Personalised Text Generation in LLMs 提出PREF框架以解决个性化文本生成评估问题 large language model
22 LLM Unlearning Without an Expert Curated Dataset 提出一种自动化生成遗忘集的方法以解决大语言模型的知识遗忘问题 large language model ✅
23 Deep Language Geometry: Constructing a Metric Space from LLM Weights 提出一种新框架利用LLM权重构建语言度量空间 large language model ✅
24 Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime 提出小规模知识注入方法以解决LLM知识获取挑战 large language model ✅
25 Pragmatics beyond humans: meaning, communication, and LLMs 提出人机沟通框架以解决大语言模型的语用学挑战 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
26 HapticLLaMA: A Multimodal Sensory Language Model for Haptic Captioning 提出HapticLLaMA以解决触觉信号描述生成问题 reinforcement learning RLHF large language model
27 GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models 提出GLM-4.5以推动智能推理与编码任务的研究 reinforcement learning large language model foundation model ✅
28 SABER: Switchable and Balanced Training for Efficient LLM Reasoning 提出SABER以解决大语言模型推理效率问题 reinforcement learning large language model chain-of-thought
29 UR$^2$: Unify RAG and Reasoning through Reinforcement Learning 提出UR$^2$以统一检索增强生成与推理能力 reinforcement learning large language model ✅
30 gpt-oss-120b & gpt-oss-20b Model Card 提出gpt-oss-120b与gpt-oss-20b以提升推理准确性与效率 reinforcement learning distillation instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页