cs.CL（2025-06-30）

📊 共 25 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

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

#题目一句话要点标签🔗⭐
1 Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting 提出MAPS框架以提升大语言模型的多步数学推理能力 large language model chain-of-thought
2 The Trilemma of Truth in Large Language Models 提出sAwMIL框架以解决大语言模型真伪性验证问题 large language model
3 Impact of Fine-Tuning Methods on Memorization in Large Language Models 提出细化调优方法以解决大语言模型的记忆泄露问题 large language model
4 Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data 提出跨领域评估方法以提升表格理解能力 multimodal
5 Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective 探讨大型语言模型在数学问题解决中的局限性 large language model
6 On Recipe Memorization and Creativity in Large Language Models: Is Your Model a Creative Cook, a Bad Cook, or Merely a Plagiator? 提出自动化框架以评估大语言模型的食谱记忆与创造力 large language model
7 Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective 提出强化微调方法以更好地保留多模态大语言模型的先前知识 large language model multimodal
8 Prompting as Scientific Inquiry 将提示视为科学探究以提升大语言模型的理解与控制 large language model chain-of-thought
9 Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs 提出统一参数集成框架以解决多模态大语言模型知识碎片化问题 large language model multimodal
10 IMPACT: Inflectional Morphology Probes Across Complex Typologies 提出IMPACT框架以评估大语言模型在形态学上的表现 large language model chain-of-thought
11 EXPERT: An Explainable Image Captioning Evaluation Metric with Structured Explanations 提出EXPERT以解决图像描述评估标准化问题 large language model ✅
12 PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER) 提出PBa-LLM以解决隐私与偏见问题 large language model
13 Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens 通过资源高效的领域自适应预训练提升网络安全LLM专业化 large language model
14 Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning 提出两阶段推理增强学习以提升文本分类性能 large language model
15 User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs 提出用户行为预测以解决LLMs泛化能力评估问题 large language model
16 LineRetriever: Planning-Aware Observation Reduction for Web Agents 提出LineRetriever以解决网页导航任务中的观察信息冗余问题 large language model
17 TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation 提出TaP框架以自动化生成多语言偏好数据集 large language model
18 Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders 提出稀疏自编码器以提升文本分类中的可解释性 large language model
19 Evaluating the Simulation of Human Personality-Driven Susceptibility to Misinformation with LLMs 评估大语言模型在个性驱动的虚假信息易感性模拟中的应用 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
20 Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning 提出自动化主题分析方法以解决传统临床叙事分析的低效问题 reinforcement learning RLHF large language model
21 Semantic-guided Diverse Decoding for Large Language Model 提出语义引导的多样解码方法以解决大语言模型的语义多样性问题 reinforcement learning RLHF large language model
22 Logit-Gap Steering: Efficient Short-Suffix Jailbreaks for Aligned Large Language Models 提出Logit-Gap Steering以高效破解对齐的大型语言模型 RLHF large language model
23 Efficient Interleaved Speech Modeling through Knowledge Distillation 提出TinyWave以解决语音生成模型体积与延迟问题 distillation multimodal
24 L0: Reinforcement Learning to Become General Agents 提出L-Zero以解决大规模自主智能体训练效率问题 reinforcement learning large language model ✅
25 Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent 提出思维增强规划以解决复杂用户意图问题 distillation large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页