cs.CL（2025-10-10）
📊 共 5 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) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Don't Throw Away Your Pretrained Model | 提出Switch Generation，通过模型协作提升语言模型综合能力 | instruction following | ||
| 2 | HIPPD: Brain-Inspired Hierarchical Information Processing for Personality Detection | HIPPD：一种脑启发的分层信息处理框架，用于人格检测 | large language model | ||
| 3 | CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs | CoBia：通过构造对话揭示LLM中潜在的社会偏见 | large language model | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Abductive Preference Learning | 提出溯因偏好学习，提升大模型对反事实提示的敏感性 | reinforcement learning preference learning RLHF | ||
| 5 | Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning | 提出基于Span级别微调的抽象摘要方法，提升生成摘要的忠实度 | contrastive learning large language model |