cs.CL（2025-05-04）

📊 共 13 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)

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

#	题目	一句话要点	标签	🔗	⭐
1	LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning	LecEval：一种用于多媒体学习中多模态知识获取的自动化评估指标	large language model multimodal	✅
2	Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview	提出社会世界观分类法以分析大型语言模型的认知差异	large language model
3	Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models	利用Debias Tuning解决大语言模型中基于地理位置的仇恨言论检测偏差问题	large language model
4	Adaptive Thinking via Mode Policy Optimization for Social Language Agents	提出AML框架，通过自适应模式策略优化提升社交语言Agent的推理能力。	chain-of-thought
5	QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach	QiMeng-Xpiler：利用神经-符号方法转译张量程序，实现深度学习系统跨平台部署	large language model
6	LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications	LLM-OptiRA：利用LLM优化无线通信中非凸资源分配问题	large language model
7	A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking	提出HOPE，一种领域无关的文本分块自动评估指标，提升RAG性能。	large language model
8	Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading	首次提出仅从阅读时的眼动追踪数据解码开放式信息搜寻目标	multimodal
9	Probing Audio-Generation Capabilities of Text-Based Language Models	探索文本语言模型音频生成能力：一种基于代码中间层的三层递进方法	large language model
10	Measuring Hong Kong Massive Multi-Task Language Understanding	提出香港多任务语言理解基准HKMMLU，评估LLM在香港语言文化环境下的能力。	large language model
11	Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization	利用大型语言模型识别法律判决要点：性能、规模与记忆的系统性研究	large language model
12	Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair Use	提出结合法律知识图谱的RAG方法，提升版权合理使用场景下的检索质量与推理可靠性	chain-of-thought

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

#	题目	一句话要点	标签	🔗	⭐
13	Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study	探索离线强化学习在提升大语言模型推理能力上的潜力	reinforcement learning offline RL DPO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页