cs.CL（2025-12-10）

📊 共 24 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning 提出基于持续学习的安全对齐方法，缓解LLM微调过程中的安全性遗忘问题 large language model
2 What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models 分析大型语言模型（LLM）的推理本质：随机性与诱导表象 large language model
3 DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting 探究大语言模型的文化倾向：提示词语言和文化引导的影响 large language model
4 MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QA MedBioRAG：利用大型语言模型进行医学和生物问答的语义搜索和检索增强生成 large language model
5 MentraSuite: Post-Training Large Language Models for Mental Health Reasoning and Assessment MentraSuite：用于心理健康推理和评估的后训练大型语言模型 large language model
6 System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection 提出一种基于Prompt驱动的大语言模型融合框架，用于细粒度中文仇恨言论检测。 large language model
7 Systematic Framework of Application Methods for Large Language Models in Language Sciences 提出LLM在语言科学中应用的系统性框架，提升研究可复现性和可靠性。 large language model
8 Advancing Text Classification with Large Language Models and Neural Attention Mechanisms 提出基于大语言模型和神经注意力机制的文本分类算法，提升长程依赖建模和类别不平衡处理能力。 large language model
9 Knowledge-Augmented Large Language Model Agents for Explainable Financial Decision-Making 提出知识增强的大语言模型Agent，用于可解释的金融决策 large language model
10 CORE: A Conceptual Reasoning Layer for Large Language Models CORE：为大语言模型设计概念推理层，提升多轮对话稳定性 large language model
11 PARAN: Persona-Augmented Review ANswering system on Food Delivery Review Dataset 提出PARAN：一种在食品配送评论数据集上基于用户画像增强的评论回复系统 large language model
12 Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models 提出Generate-Then-Validate框架，利用小型语言模型进行高质量问题生成。 large language model
13 Mitigating Social Bias in English and Urdu Language Models Using PRM-Guided Candidate Selection and Sequential Refinement 提出PRM引导的候选选择与序列精炼方法，缓解英乌语言模型中的社会偏见。 large language model
14 LLMs in Interpreting Legal Documents 探索LLM在法律文档解读中的应用，优化法律任务并提升信息检索效率 large language model
15 Creation of the Estonian Subjectivity Dataset: Assessing the Degree of Subjectivity on a Scale 创建爱沙尼亚语主观性数据集，用于评估文档级主观程度 large language model
16 Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search 提出基于束搜索的方法以改善LLM的不确定性量化 large language model
17 Complexity Agnostic Recursive Decomposition of Thoughts 提出CARD框架，通过预判问题复杂度自适应分解思路，提升大语言模型推理效率与准确率。 large language model
18 Training-free Context-adaptive Attention for Efficient Long Context Modeling 提出TCA-Attention，一种免训练的上下文自适应注意力机制，用于高效长文本建模。 large language model
19 Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment 提出基于冲突感知的框架SHF-CAS，提升奖励模型对齐中LLM的性能。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
20 KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering 提出KBQA-R1框架，通过强化学习优化LLM在知识库问答中的推理能力。 reinforcement learning large language model
21 ChronusOmni: Improving Time Awareness of Omni Large Language Models ChronusOmni：提升全模态大语言模型的时间感知能力，解决跨模态时序推理问题 reinforcement learning large language model
22 RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning 提出RouteRAG以解决图文混合检索生成的效率问题 reinforcement learning large language model
23 LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach 提出LEXMA框架，利用强化学习微调LLM，为业务决策生成可解释性文本。 reinforcement learning large language model
24 d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models d-TreeRPO：面向扩散语言模型，提升策略优化的可靠性 reinforcement learning distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页