cs.CL（2025-10-25）

📊 共 14 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Irony Detection in Urdu Text: A Comparative Study Using Machine Learning Models and Large Language Models	利用机器和大型语言模型，解决乌尔都语文本中的反讽检测问题	large language model
2	Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling	提出基于内存的语言模型，实现高效、可解释、环保的大语言建模	large language model
3	From Slides to Chatbots: Enhancing Large Language Models with University Course Materials	提出多模态检索增强生成方法以提升大学课程LLM性能	large language model
4	Estimating the Error of Large Language Models at Pairwise Text Comparison	提出一种无需ground truth的成对文本比较中大语言模型误差估计方法	large language model
5	Evaluating LLMs' Reasoning Over Ordered Procedural Steps	评估LLM在排序程序步骤上的推理能力，以食谱重建为场景	large language model
6	Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection	提出CAP数据集，用于检测科学文本生成中大型语言模型的幻觉问题。	large language model
7	FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation	提出FAIR-RAG，通过可信自适应迭代优化检索增强生成，提升复杂问答任务性能。	large language model
8	SteerX: Disentangled Steering for LLM Personalization	SteerX：用于LLM个性化的解耦引导方法，提升用户偏好对齐	large language model
9	You Don't Need Prompt Engineering Anymore: The Prompting Inversion	提出Prompting Inversion现象：提示工程策略需随LLM能力演进	chain-of-thought
10	DETECT: Determining Ease and Textual Clarity of German Text Simplifications	提出DETECT：一种用于评估德语文本简化质量的指标，无需人工标注。	large language model
11	Surface Reading LLMs: Synthetic Text and its Styles	提出“表面完整性”视角，分析大型语言模型生成的文本风格，揭示其文化机器属性。	large language model
12	PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination	构建PANORAMA数据集，模拟专利审查决策过程，评估LLM在专利审查中的能力	large language model	✅
13	Generalization or Memorization: Dynamic Decoding for Mode Steering	提出动态模式引导（DMS）算法，提升大语言模型推理时逻辑一致性和事实准确性。	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	🔗	⭐
14	VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations	提出VisJudge-Bench，用于评估多模态大语言模型在可视化美学和质量评估方面的能力，并提出VisJudge模型。	MAE large language model multimodal	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页