cs.CL（2026-03-06）

📊 共 26 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing 提出BRTR：基于Agent的迭代式检索框架，用于多模态电子表格理解与编辑。 large language model multimodal
2 SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models SPOT：通过跨度级暂停思想提升大语言模型推理效率与可解释性 large language model chain-of-thought
3 Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models 结合个体与情境，利用大语言模型预测社交媒体用户的心理健康状态。 large language model
4 ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning ROSE：重排序的SparseGPT，提升大语言模型单次剪枝的准确性 large language model ✅
5 Abductive Reasoning with Syllogistic Forms in Large Language Models 探索大语言模型在基于三段论形式的溯因推理能力 large language model
6 Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring 利用大语言模型评估奥地利A-Level德语作文，探索自动作文评分 large language model
7 PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models PVminerLLM：利用大语言模型结构化提取患者自述文本中的患者声音 large language model
8 Evaluation of Deontic Conditional Reasoning in Large Language Models: The Case of Wason's Selection Task 提出蕴含义务情态的Wason选择任务数据集，评估大语言模型在义务条件推理中的表现。 large language model
9 Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI 提出基于Transformer的数学实体关系抽取模型，并结合XAI提升透明度 large language model
10 LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation LIT-RAGBench：用于评估大型语言模型在检索增强生成中生成能力的基准测试 large language model ✅
11 Wisdom of the AI Crowd (AI-CROWD) for Ground Truth Approximation in Content Analysis: A Research Protocol & Validation Using Eleven Large Language Models 提出AI-CROWD协议，利用LLM集成输出近似内容分析的真值标准。 large language model
12 HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models HART：数据驱动的大语言模型幻觉溯源与证据追踪框架 large language model
13 RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning 提出RouteGoT以解决图结构推理中的成本效率问题 large language model chain-of-thought
14 PONTE: Personalized Orchestration for Natural Language Trustworthy Explanations PONTE：面向自然语言可信解释的个性化编排框架 large language model
15 FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling FlashPrefill：通过即时模式发现和阈值处理加速长文本预填充 large language model
16 Making Implicit Premises Explicit in Logical Understanding of Enthymemes 提出一种结合LLM和神经符号推理的框架，用于补全和理解蕴含前提的论证。 large language model
17 Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality 通过领域特定预训练塑造LLM人格，提升问题解决能力 large language model
18 MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing MASFactory：基于图结构的LLM多智能体系统编排框架，提升可复用性和可扩展性 large language model ✅
19 Lost in Stories: Consistency Bugs in Long Story Generation by LLMs 提出ConStory-Bench基准测试，评估大型语言模型在长篇故事生成中的一致性问题。 large language model ✅
20 Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion 提出多语言审计方法以解决LLM与亚洲公众意见的文化不对齐问题 large language model
21 Learning Next Action Predictors from Human-Computer Interaction 提出LongNAP模型，通过预测用户在人机交互中的下一步动作，实现更主动的AI系统。 multimodal
22 VerChol -- Grammar-First Tokenization for Agglutinative Languages VerChol：面向粘着语的语法优先分词方法，提升LLM性能。 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🔗⭐
23 ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning ReflexiCoder：通过强化学习教大型语言模型自省和自纠代码 reinforcement learning large language model ✅
24 Implicit Style Conditioning: A Structured Style-Rewrite Framework for Low-Resource Character Modeling 提出隐式风格调节框架，解决低资源场景下角色建模的风格一致性问题。 distillation large language model chain-of-thought
25 From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring 对比研究LLM在自动作文评分中的应用，揭示不同策略的权衡与优势。 DPO direct preference optimization large language model ✅
26 Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation 提出CoCA框架，在LLM回答前预测置信度，提升不确定性估计效率。 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页