cs.CL（2025-09-01）

📊 共 29 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Natural Context Drift Undermines the Natural Language Understanding of Large Language Models 提出框架分析自然文本演变对LLM问答能力的影响 large language model
2 Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition 提出序列化输出提示以提升多说话者语音识别性能 large language model
3 Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation 评估大型语言模型在伊斯兰继承法推理中的表现 large language model ✅
4 REFRAG: Rethinking RAG based Decoding 提出REFRAG以解决RAG解码效率问题 large language model
5 Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning Vis-CoT：人机协同交互式可视化LLM思维链推理框架 large language model chain-of-thought
6 Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors 深入探究思维链：上下文学习与预训练先验的双重角色 large language model chain-of-thought
7 CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models 提出因果注意力调整（CAT）方法，将细粒度因果知识注入大型语言模型。 large language model ✅
8 Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal UniCR：提出统一框架，通过校准不确定性证据实现大语言模型风险可控的拒绝回答 large language model
9 On the Alignment of Large Language Models with Global Human Opinion 提出基于世界价值观调查的框架，评估大语言模型与全球人类意见的对齐程度 large language model ✅
10 Can Large Language Models Master Complex Card Games? 探索LLM在复杂卡牌游戏中的能力：通过微调实现类人智能 large language model ✅
11 DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression DaMoC：基于数据和模型压缩高效选择领域任务微调的最佳大语言模型 large language model
12 Efficient Large Language Models with Zero-Shot Adjustable Acceleration 提出零样本可调加速方法，提升大语言模型推理效率 large language model
13 WATCHED: A Web AI Agent Tool for Combating Hate Speech by Expanding Data 提出WATCHED，一种基于Web AI Agent的内容审核工具，用于检测和解释仇恨言论。 large language model chain-of-thought
14 ShortageSim: Simulating Drug Shortages under Information Asymmetry ShortageSim：首个信息不对称下药品短缺监管干预的模拟框架 large language model
15 Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs 重新审视LLM的prompt敏感性：评估方法伪像还是模型缺陷？ large language model
16 Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations 评估LLM在学术推荐中的公平性：揭示并量化语言模型中的偏见 large language model
17 Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry 构建现代中文诗歌检测基准，评估现有方法在识别LLM生成诗歌上的局限性 large language model
18 Do Retrieval Augmented Language Models Know When They Don't Know? 研究检索增强语言模型（RALM）的拒识能力，并提出改进方案。 large language model
19 Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA 提出Reason-KE框架，通过显式推理链实现对LLM的鲁棒知识编辑，提升多跳QA抗干扰能力。 large language model
20 LLMs cannot spot math errors, even when allowed to peek into the solution LLM难以发现数学解题步骤中的错误，即使允许查看参考答案 large language model
21 LongCat-Flash Technical Report LongCat-Flash：一个具有高效计算和高级Agent能力的5600亿参数MoE语言模型 foundation model ✅
22 Culture is Everywhere: A Call for Intentionally Cultural Evaluation 提出“有意文化评估”框架，解决LLM文化对齐评估中存在的偏见问题 large language model
23 Mitigating Catastrophic Forgetting in Continual Learning through Model Growth 通过模型增长缓解持续学习中的灾难性遗忘 large language model
24 Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective 提出实体对齐翻译方法，解决零样本跨语言命名实体识别中非拉丁语系性能下降问题 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🔗⭐
25 We Politely Insist: Your LLM Must Learn the Persian Art of Taarof 提出TaarofBench以解决大语言模型的文化理解问题 direct preference optimization large language model
26 Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic 通过任务算术迁移Chain-of-Thought能力：提取并复用LLM推理向量 reinforcement learning large language model chain-of-thought
27 Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning 提出SAT框架，通过结构感知对齐微调增强LLM的知识图谱补全能力 contrastive learning large language model
28 Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief EAGLE：利用LLM内部信念聚合期望提升不确定性估计 reinforcement learning RLHF large language model
29 Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation 提出一种模块化框架，用于合成长文本数据，以提升语言模型训练和评估效果。 DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页