cs.CL（2026-02-08）

📊 共 13 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗2) 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 Cross-Linguistic Persona-Driven Data Synthesis for Robust Multimodal Cognitive Decline Detection SynCog：跨语言的、基于人物驱动的数据合成，用于稳健的多模态认知衰退检测 large language model multimodal chain-of-thought
2 Gender and Race Bias in Consumer Product Recommendations by Large Language Models 揭示大型语言模型在消费品推荐中存在的性别和种族偏见 large language model
3 SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization SparseEval：通过稀疏优化实现大语言模型的高效评估 large language model ✅
4 Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models 提出基于合作博弈的LLM剪枝方法，利用代理模型估计层贡献度 large language model
5 Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models 揭示大语言模型中涌现的结构化表征如何支持灵活的上下文推理 large language model
6 The Algorithmic Unconscious: Structural Mechanisms and Implicit Biases in Large Language Models 揭示大语言模型“算法无意识”：结构性机制与内隐偏见分析 large language model
7 Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning DIP：发散诱导提示，通过多策略归纳提升零样本推理能力 large language model chain-of-thought
8 Emergent Search and Backtracking in Latent Reasoning Models 研究表明，隐式推理模型在潜在空间中涌现搜索和回溯能力，提升问答性能。 chain-of-thought
9 Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms 提出CompositeHarm基准，评估LLM在跨语言场景下复合危害的迁移能力 large language model
10 Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation Bielik Guard：高效的波兰语LLM内容审核安全分类器 large language model
11 Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents 强制思考降低LLM Agent交互性：用户交互场景下思考提示可能适得其反 large language model ✅
12 Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs 提出Attn-GS，利用注意力机制引导上下文压缩，提升个性化LLM效率。 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 Patches of Nonlinearity: Instruction Vectors in Large Language Models 揭示大语言模型指令向量：非线性交互与电路选择机制 DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页