cs.CL（2025-01-04）

📊 共 6 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving	提出基于LLM的合成审议方法，解决复杂问题求解中多视角融合难题	large language model
2	Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection	提出基于自反思的框架，揭示大语言模型中显性与隐性社会偏见的不一致性。	large language model
3	Personalized Graph-Based Retrieval for Large Language Models	提出PGraphRAG，利用个性化图谱提升大语言模型在冷启动场景下的检索增强生成效果	large language model
4	AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference	AdaSkip：面向长文本LLM推理的自适应子层跳跃加速方法	large language model
5	Validity Arguments For Constructed Response Scoring Using Generative Artificial Intelligence Applications	针对生成式AI在开放式问答评分中的应用，提出一套验证性证据收集的最佳实践。	large language model

#	题目	一句话要点	标签	🔗	⭐
6	REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization	提出REINFORCE++，通过全局优势归一化稳定无Critic策略优化，提升RLHF性能。	reinforcement learning PPO RLHF