cs.CL（2026-09-08）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱二：RL算法与架构 (RL & Architecture) (7)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Evaluation of Contextual Understanding in Large Language Models 提出基于知识图谱的评估框架以提升大语言模型的上下文理解能力 large language model
2 Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models 提出政治坐标测试框架以评估大语言模型的政治偏见与公平性 large language model
3 Do Reviewers Still Reward Lexical Complexity? A Frozen-Rater Study of Preference Drift in 124K ICLR Reviews 提出冷冻评审者模型以分析ICLR评审偏好变化 large language model
4 Measuring LLM Sycophancy under Sustained Multi-Turn Pressure 提出SPINE基准以评估LLM在持续压力下的谄媚行为 large language model
5 Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation 提出REAL框架以提升LLM的证据依赖性和事实核查能力 large language model
6 Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values 提出C-Voices数据集与价值向量引导方法以解决多语言价值对齐问题 large language model
7 It's Not RoPE that Creates Sinks: The Role of Self-Concentration and Value-Non-Mixing in Attention 分析自集中与价值非混合在注意力机制中的作用 large language model
8 Combating Instruction Conflict via Energy-Driven Latent Conflict Detection 提出ELCD以解决大语言模型中的指令冲突问题 large language model
9 Compositional Multilingual and Behavioral Attribute Steering 提出复合多语言与行为属性引导方法以提升大语言模型控制能力 large language model
10 EviSI: An Evaluation Agent for Simultaneous Interpreting 提出EviSI以解决同声传译评估问题 large language model
11 Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation 提出Jacap以解决KV缓存驱逐中的信息容量保持问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
12 Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representation 提出统一语言表示以解决多模态问答系统的挑战 MAE multimodal
13 AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing 提出AuK模型以统一语音生成与编辑任务 reinforcement learning classifier-free guidance large language model
14 Global Divergence, Local Convergence: Representation Geometry in SSMs and Transformers 研究SSMs与Transformers的表示几何特性以揭示其功能收敛性 Mamba SSM
15 Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents 提出Experience Funnel以解决自我进化智能体的适应与能力提升问题 distillation large language model
16 Which Forms of Caregiver Feedback Support Grammar Learning? A Reinforcement-Learning Study of Child-Like Language Models 提出基于强化学习的反馈机制以支持儿童语法学习 reinforcement learning
17 NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness 提出NeoHorse-1以实现递归自我改进的智能后训练机制 distillation instruction following
18 When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation 提出CuRIL框架以解决社交媒体翻译评估中的文化推理问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页