cs.CL（2026-03-16）

📊 共 21 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) (15 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Decision-Level Ordinal Modeling for Multimodal Essay Scoring with Large Language Models 提出决策级序数建模(DLOM)用于提升大语言模型在多模态作文评分中的性能。 large language model multimodal
2 Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models 提出RoSE，解决大语言模型同主题知识编辑中的泛化性崩溃问题 large language model instruction following
3 Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs 提出AdaAnchor以解决LLMs推理效率低下问题 large language model chain-of-thought
4 A Closer Look into LLMs for Table Understanding 深入研究LLM在表格理解中的应用，揭示其内部机制与性能影响因素 large language model chain-of-thought
5 CCTU: A Benchmark for Tool Use under Complex Constraints CCTU：一个用于复杂约束下工具使用的评测基准 large language model instruction following
6 OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora OrgForge：用于可验证合成公司语料库的多智能体仿真框架 large language model TAMP
7 Towards Next-Generation LLM Training: From the Data-Centric Perspective 面向下一代LLM训练：从数据中心视角出发，构建自动化数据准备与动态数据-模型交互系统 large language model
8 Mixture-of-Depths Attention 提出混合深度注意力机制(MoDA)，解决深度语言模型中的信号衰减问题。 large language model ✅
9 Mechanistic Origin of Moral Indifference in Language Models 揭示并缓解大语言模型中道德冷漠的机制性根源 large language model
10 Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation 利用LLM生成错误答案：分析其模拟学生错误推理的能力 large language model
11 CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents CLAG：基于Agent驱动聚类的自适应记忆组织，提升小语言模型Agent性能 large language model
12 When Does Sparsity Mitigate the Curse of Depth in LLMs 揭示LLM深度利用率瓶颈，提出稀疏性缓解深度诅咒的机制 large language model ✅
13 Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategies 构建多语言动词交替数据集，用于评估LLM的跨句法语义推理能力。 large language model
14 Practicing with Language Models Cultivates Human Empathic Communication 利用语言模型训练提升人类共情沟通能力 large language model
15 The Hrunting of AI: Where and How to Improve English Dialectal Fairness 研究表明数据质量和可得性影响LLM在英语方言上的公平性提升，并提出改进建议。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
16 MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge 提出MMKU-Bench，用于评估多模态模型在知识更新方面的表现，涵盖已知与未知知识。 reinforcement learning RLHF multimodal
17 Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models Fusian：多LoRA融合实现大语言模型中细粒度连续MBTI人格控制 reinforcement learning large language model
18 Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning Code-A1：通过强化学习对抗进化代码LLM和测试LLM，提升代码生成质量。 reinforcement learning
19 Criterion-referenceability determines LLM-as-a-judge validity across physics assessment formats 研究表明，LLM作为评分者的有效性取决于物理评估任务的标准参照性 MAE large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
20 LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy 利用信号检测理论分析LLM：揭示温度参数与决策标准的类比及局限性 manipulation large language model
21 The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatments 研究意识形态文本对RAG模型输出的影响，以COVID-19治疗为例。 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页