cs.AI（2025-12-17）
📊 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) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Cross-Language Bias Examination in Large Language Models | 提出多语言偏见评估框架，揭示大型语言模型在不同语言间的偏见差异。 | large language model | ||
| 2 | Explaining the Reasoning of Large Language Models Using Attribution Graphs | 提出CAGE框架，通过归因图解释大型语言模型的推理过程，提升归因忠实度。 | large language model | ||
| 3 | Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in Large Language Models | 研究揭示大型语言模型在网络叙事中内化了人类信任感知的认知-情感特征。 | large language model | ✅ | |
| 4 | "They parted illusions -- they parted disclaim marinade": Misalignment as structural fidelity in LLMs | 从结构保真角度解读LLM对齐问题，而非简单归咎于欺骗性意图 | large language model chain-of-thought | ||
| 5 | ChatGPT and Gemini participated in the Korean College Scholastic Ability Test -- Earth Science I | 分析大型语言模型在韩国高考地球科学中的推理能力与局限性，为设计抗AI试题提供依据 | large language model multimodal |