cs.CL（2025-08-29）

📊 共 22 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

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

#题目一句话要点标签🔗⭐
1 Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models 提出Med-RewardBench以解决医疗多模态大语言模型评估问题 large language model multimodal
2 Challenges and Applications of Large Language Models: A Comparison of GPT and DeepSeek family of models 比较GPT与DeepSeek模型以应对大型语言模型的挑战 large language model
3 Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Study 提出基于CFA的基准研究以评估大型语言模型在金融推理中的表现 large language model
4 Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval 提出RITE以解决复杂查询的文档检索问题 large language model
5 Beyond the Surface: Probing the Ideological Depth of Large Language Models 提出意识深度概念以分析大型语言模型的政治倾向 large language model
6 Is this chart lying to me? Automating the detection of misleading visualizations 提出Misviz基准以自动检测误导性可视化 large language model multimodal
7 Morae: Proactively Pausing UI Agents for User Choices 提出Morae以解决盲人及低视力用户的UI选择问题 multimodal
8 Going over Fine Web with a Fine-Tooth Comb: Technical Report of Indexing Fine Web for Problematic Content Search and Retrieval 提出基于ElasticSearch的框架以提升LLM训练数据索引与分析 large language model
9 PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains 提出PiCSAR以解决推理链评分问题 large language model
10 Reasoning-Intensive Regression 提出MENTAT以解决推理密集型回归问题 large language model
11 QZhou-Embedding Technical Report 提出QZhou-Embedding以提升文本嵌入模型的表示能力 foundation model
12 Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning 提出Middo框架以解决LLM训练数据优化问题 large language model ✅
13 A Survey on Current Trends and Recent Advances in Text Anonymization 综述文本匿名化技术以应对隐私保护挑战 large language model
14 COCORELI: Cooperative, Compositional Reconstitution \& Execution of Language Instructions 提出COCORELI以解决复杂指令执行中的局限性问题 large language model
15 Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing 基于多模态视觉的发票处理策略比较研究 large language model
16 Normality and the Turing Test 通过正常性概念重新审视图灵测试 large language model
17 Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance 提出核心参数隔离微调框架以提升大语言模型性能 large language model
18 Discovering Semantic Subdimensions through Disentangled Conceptual Representations 提出解耦概念表示模型以发现语义子维度 large language model
19 Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework 提出自动化反事实评估框架以检测研究论文中的逻辑缺陷 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
20 Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics 提出状态感知转移框架以增强链式思维推理的可解释性 latent dynamics large language model chain-of-thought
21 Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards 提出RLAIF框架以提升小型语言模型的创意写作能力 reinforcement learning RLHF large language model ✅
22 RECAP: REwriting Conversations for Intent Understanding in Agentic Planning 提出RECAP以解决对话意图理解问题 DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页