cs.CL（2025-04-19）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

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

#题目一句话要点标签🔗⭐
1 SConU: Selective Conformal Uncertainty in Large Language Models SConU：通过选择性一致性不确定性，提升大语言模型在实际应用中的可靠性。 large language model
2 Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations 提出一种评估大型语言模型解释忠实度的新方法，揭示模型解释与实际推理的偏差。 large language model
3 Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites 提出基于MAP-Elites的提示工程方法，提升大语言模型在多样化任务中的性能。 large language model
4 Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach 提出TikTalkCoref数据集，并构建基准方法，解决中文社交媒体对话中的多模态共指消解问题。 multimodal
5 PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models 综述：针对大语言和视觉模型的参数高效微调（PEFT）技术 large language model multimodal
6 Density Measures for Language Generation 提出基于密度测度的语言生成算法，解决有效性和广度之间的权衡问题 large language model
7 Mind the Language Gap: Automated and Augmented Evaluation of Bias in LLMs for High- and Low-Resource Languages MLA-BiTe框架：自动化增强多语言偏见测试，填补LLM低资源语言偏见评估空白 large language model
8 SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification SimplifyMyText：一个基于LLM的包容性纯语言文本简化系统 large language model
9 Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification 提出一种高效的标注流程，用于分析和缓解预训练语料库中的社会偏见。 large language model
10 Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models Meta-rater：一种面向预训练语言模型的多维度数据选择方法 large language model ✅
11 Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion 质疑LLM查询扩展：基准测试中知识泄露可能高估性能 large language model
12 Self-Correction Makes LLMs Better Parsers 提出自校正方法，提升大语言模型在句法分析任务中的性能 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 Probing the Subtle Ideological Manipulation of Large Language Models 提出多任务数据集以探讨大型语言模型的意识形态操控 manipulation large language model
14 Understanding the Repeat Curse in Large Language Models from a Feature Perspective 提出Duplicatus Charm方法，从特征角度理解并缓解大语言模型中的重复生成问题。 manipulation 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🔗⭐
15 Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models 研究Transformer到亚二次复杂度语言模型的知识蒸馏效果，探索高效模型压缩方案 SSM linear attention distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页