cs.CL（2025-07-20）

📊 共 14 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction 评估大语言模型在Meta分析数据抽取中的自动化水平，并提出实用指南。 large language model
2 Theoretical Foundations and Mitigation of Hallucination in Large Language Models 本文为大语言模型幻觉问题提供理论基础、检测方法与缓解策略。 large language model
3 MUR: Momentum Uncertainty guided Reasoning for Large Language Models 提出动量不确定性引导推理以提升大语言模型的推理效率 large language model
4 From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment 提出 NeuronXA，通过神经元对齐评估大型语言模型跨语言对齐能力 large language model
5 Filling the Gap: Is Commonsense Knowledge Generation useful for Natural Language Inference? 探索常识知识生成对自然语言推理的效用，利用大语言模型弥补知识鸿沟。 large language model
6 WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization 提出WebShaper以解决信息检索代理数据合成问题 large language model
7 A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations 提出Penalty-Adjusted Type-Token Ratio (PATTR)，解决提示影响下合成文本长度变化导致的词汇多样性度量偏差问题。 large language model
8 Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs 提出SASFT方法，通过稀疏自编码器指导监督微调，显著缓解LLM中意外的代码切换问题 large language model
9 MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction MEKiT：一种用于情感原因对抽取的指令调优多源异构知识注入方法 large language model
10 Tiny language models 探索小型语言模型：验证其预训练有效性及可扩展性，降低NLP研究门槛 large language model ✅
11 Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents Doc2Chart：提出意图驱动的文档零样本图表生成框架 large language model
12 FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing FastLongSpeech：通过迭代融合和动态压缩训练，提升LSLM在长语音处理中的效率。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback RefCritic：利用精细化反馈训练长链思考评论模型 reinforcement learning large language model chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Full Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphs 提出全三元组匹配方法以解决异构知识图谱集成问题 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页