cs.CL（2025-03-20）

📊 共 34 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗3) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions 综述分布式LLM与多模态LLM，分析其进展、挑战与未来方向 large language model multimodal
2 Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models 利用检索增强生成技术提升大型语言模型在古兰经研究中的准确性和可靠性 large language model
3 Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs 利用大型语言模型和知识图谱加速抗生素发现 large language model
4 Leveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation 利用大语言模型提升智能家居中活动识别的可解释性 large language model
5 CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models 提出CodeReviewQA，用于评估大型语言模型在代码评审理解方面的能力。 large language model
6 Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models 提出基于政治科学理论的LLM政治倾向评估方法，克服传统方法局限性。 large language model ✅
7 MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering MKG-Rank：利用知识图谱增强大语言模型，实现多语言医学问答 large language model
8 Corrective In-Context Learning: Evaluating Self-Correction in Large Language Models 提出纠正性上下文学习(CICL)，探索LLM的自纠错能力，但实验表明其性能不如标准ICL。 large language model
9 ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph ECKGBench：利用知识图谱评估电商领域大语言模型的事实性 large language model
10 From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models 提出原子推理器框架，提升大语言模型细粒度逻辑推理能力 large language model
11 Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey 针对大语言模型不确定性量化与置信度校准的综述研究 large language model
12 CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners CaKE：通过电路感知编辑实现知识学习器的泛化能力提升 large language model ✅
13 Design and Implementation of an FPGA-Based Hardware Accelerator for Transformer 针对Transformer的QKV投影，提出一种高效FPGA硬件加速器设计。 large language model
14 A Comprehensive Survey on Long Context Language Modeling 针对长文本处理难题，综述长上下文语言模型（LCLM）的最新进展与未来方向。 large language model ✅
15 FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article FutureGen：一种基于RAG的方法，用于生成科学文章的未来工作建议。 large language model
16 MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion MathFusion：通过指令融合增强LLM的数学问题求解能力 large language model ✅
17 Towards Lighter and Robust Evaluation for Retrieval Augmented Generation 提出轻量级RAG评估方法，利用量化LLM实现低成本、可解释的幻觉检测。 large language model
18 Tuning LLMs by RAG Principles: Towards LLM-native Memory 提出RAG-Tuned-LLM，结合长文本LLM和RAG优势，提升LLM在记忆增强任务中的性能。 large language model
19 The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement 提出基于评论指导改进（CGI）框架，提升LLM Agent在交互环境中的决策能力。 large language model
20 Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models 提出CK-PLUG以解决语言模型知识依赖控制问题 large language model ✅
21 Fùxì: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation Fùxì：一个用于评估语言模型在古文理解与生成能力上的基准 large language model
22 How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities 提出DSC基准，揭示基于偏好数据的LLM路由器的脆弱性与安全风险 large language model
23 Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Markets 通过苏格拉底式探究揭示LLM在意识形态框架偏见上的潜在倾向 large language model
24 LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates LLMBRACES：通过相关子更新调整LLM预测，提升性能并实现风格控制。 large language model
25 SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs SpeCache：通过推测性键值缓存加速长文本LLM生成，解决VRAM瓶颈。 large language model
26 Meta-Learning Neural Mechanisms rather than Bayesian Priors 通过元学习神经机制而非贝叶斯先验提升模型泛化能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
27 Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning 提出Fin-R1：一个通过强化学习进行金融推理的大语言模型 reinforcement learning large language model chain-of-thought ✅
28 Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models 针对大语言模型推理效率低下问题，提出高效推理方法综述 reinforcement learning large language model chain-of-thought ✅
29 More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models 揭示大语言模型中性别偏见悖论：女性角色过度代表与刻板印象强化 reinforcement learning RLHF large language model
30 Cultural Alignment in Large Language Models Using Soft Prompt Tuning 提出基于软提示调优的文化对齐方法，提升大语言模型在跨文化场景下的表现 reinforcement learning large language model
31 Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond 评估测试时扩展LLM在法律推理中的表现：OpenAI o1、DeepSeek-R1及其他模型 distillation large language model chain-of-thought
32 WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching WaveFM：一种基于流匹配的高保真高效声码器，用于mel谱条件下的语音合成。 flow matching distillation
33 Grammar and Gameplay-aligned RL for Game Description Generation with LLMs 提出基于强化学习的LLM微调方法RLGDG，提升游戏描述生成的语法正确性和概念保真度。 reinforcement learning large language model ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
34 Deceptive Humor: A Synthetic Multilingual Benchmark Dataset for Bridging Fabricated Claims with Humorous Content 提出Deceptive Humor数据集，用于评估幽默内容掩盖下的虚假信息识别 HuMoR

⬅️ 返回 cs.CL 首页 · 🏠 返回主页