cs.CL（2025-03-16）

📊 共 13 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) (12 🔗5) 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	Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models	揭示LLM地理推荐中的偏见：美国城市推荐的公平性分析	large language model
2	Multi-Granular Multimodal Clue Fusion for Meme Understanding	提出多粒度多模态线索融合模型，提升Meme理解能力	multimodal
3	Investigating Human-Aligned Large Language Model Uncertainty	研究大型语言模型不确定性与人类认知对齐，提升模型可控性和用户信任	large language model
4	SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression	提出SVD-LLM V2以优化大语言模型压缩中的奇异值截断问题	large language model	✅
5	Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility	注入LLM知识提升事件合理性判断：一种参数高效的知识融合方法	large language model	✅
6	RaSA: Rank-Sharing Low-Rank Adaptation	提出RaSA：通过层间秩共享增强LoRA在代码生成和数学推理中的性能	large language model	✅
7	From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations	CPER框架通过动态检测和修正知识差距，提升LLM多轮对话中的个性化和连贯性。	large language model
8	CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences	CAKE：基于层偏好的级联自适应KV缓存淘汰方法，提升长序列LLM推理效率	large language model	✅
9	Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability	提出基于LLMs的隐私政策自动分析方法以提升分类性能	large language model
10	HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs	HKCanto-Eval：用于评估LLM粤语理解和文化理解能力的基准	large language model	✅
11	Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science	利用大型语言模型辅助跨学科系统科学的文献综述案例研究	large language model
12	Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs	提出CTCL框架，无需微调大型LLM即可合成保护隐私的文本数据	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	Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models	提出层级奖励模型(HRM)与层级节点压缩(HNC)策略，提升LLM推理能力并降低数据标注成本。	reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页