cs.CL（2025-06-19）

📊 共 29 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) (24 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Large Language Models in Argument Mining: A Survey 综述大型语言模型在论证挖掘中的应用与挑战 large language model multimodal chain-of-thought
2 FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning 提出FinCoT框架以提升金融领域的推理能力 large language model chain-of-thought
3 GeoGuess: Multimodal Reasoning based on Hierarchy of Visual Information in Street View 提出GeoGuess以解决多模态推理中的层次视觉信息问题 multimodal
4 Can structural correspondences ground real world representational content in Large Language Models? 探讨结构对应关系在大型语言模型中的现实内容表征问题 large language model
5 BiMark: Unbiased Multilayer Watermarking for Large Language Models 提出BiMark以解决大语言模型水印识别问题 large language model
6 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models 提出BEAT以解决大型语言模型的后门不对齐问题 large language model
7 OJBench: A Competition Level Code Benchmark For Large Language Models 提出OJBench以评估大型语言模型的代码推理能力 large language model
8 InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems 提出InstructTTSEval以解决TTS系统复杂指令理解问题 instruction following
9 Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning 提出自我批评引导的好奇心优化以提升大型语言模型的诚实性与帮助性 large language model
10 A Scoping Review of Synthetic Data Generation for Biomedical Research and Applications 综述合成数据生成技术以应对生物医学研究中的数据稀缺问题 large language model multimodal
11 Operationalizing Automated Essay Scoring: A Human-Aware Approach 提出人性化的自动化作文评分系统以解决准确性与可解释性问题 large language model
12 DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling 提出DynScaling以解决大语言模型推理效率问题 large language model
13 StoryWriter: A Multi-Agent Framework for Long Story Generation 提出StoryWriter框架以解决长篇故事生成中的连贯性与复杂性问题 large language model
14 NepaliGPT: A Generative Language Model for the Nepali Language 提出NepaliGPT以解决尼泊尔语生成模型缺失问题 large language model
15 JETHICS: Japanese Ethics Understanding Evaluation Dataset 提出JETHICS数据集以评估AI模型的伦理理解能力 large language model
16 Under the Shadow of Babel: How Language Shapes Reasoning in LLMs 提出BICAUSE数据集以验证语言对LLMs推理的影响 large language model
17 Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion 提出多模态融合方法以解决AI生成歌词检测问题 multimodal ✅
18 Arch-Router: Aligning LLM Routing with Human Preferences 提出Arch-Router以解决LLM路由与人类偏好不一致问题 large language model ✅
19 Capturing Visualization Design Rationale 提出一种新方法以探讨可视化设计的合理性 large language model
20 REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing 提出REIS以解决检索增强生成中的数据检索瓶颈问题 large language model
21 RiOT: Efficient Prompt Refinement with Residual Optimization Tree 提出RiOT框架以解决自动提示优化中的多样性与语义漂移问题 large language model
22 PL-Guard: Benchmarking Language Model Safety for Polish 提出PL-Guard以解决波兰语语言模型安全性评估问题 large language model
23 SGIC: A Self-Guided Iterative Calibration Framework for RAG 提出自指导迭代校准框架SGIC以提升RAG模型性能 large language model
24 Reranking-based Generation for Unbiased Perspective Summarization 提出基于重排序的生成方法以解决无偏见视角摘要问题 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🔗⭐
25 Measuring (a Sufficient) World Model in LLMs: A Variance Decomposition Framework 提出方差分解框架以评估大型语言模型的世界模型 world model large language model
26 Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples 提出RELIC框架以解决低资源印地语奖励模型泛化问题 RLHF large language model
27 From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling 提出多模型协作注释框架AutoAnnotator以解决大语言模型成本高和精度低的问题 reinforcement learning large language model ✅
28 From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation 提出ProxyReward以提升长文本生成模型的表现 reinforcement learning large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
29 Structured Attention Matters to Multimodal LLMs in Document Understanding 提出结构化注意力以提升多模态大语言模型的文档理解能力 spatial relationship large language model multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页