cs.CL（2025-06-18）

📊 共 40 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) (32 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (32 篇)

#题目一句话要点标签🔗⭐
1 Evaluating Multimodal Large Language Models on Educational Textbook Question Answering 评估多模态大语言模型在教材问答任务中的表现 large language model multimodal
2 Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability 提出Ordered CommonGen基准以评估LLMs的组合泛化与指令遵循能力 large language model instruction following
3 SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification 提出SciVer以评估多模态科学声明验证中的基础模型能力 foundation model multimodal
4 The Compositional Architecture of Regret in Large Language Models 提出新方法以识别和分析大语言模型中的遗憾机制 large language model
5 WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts 提出WikiMixQA基准以解决多模态文档理解问题 multimodal
6 Gender Inclusivity Fairness Index (GIFI): A Multilevel Framework for Evaluating Gender Diversity in Large Language Models 提出GIFI以评估大型语言模型的性别多样性 large language model
7 PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction 提出PredGen以解决大语言模型实时语音交互中的延迟问题 large language model
8 COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation 提出COSMMIC以解决印度语言多模态摘要生成问题 multimodal
9 DeVisE: Behavioral Testing of Medical Large Language Models 提出DeVisE框架以评估医疗大语言模型的行为表现 large language model
10 PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding 提出PaceLLM以解决长上下文理解问题 large language model
11 A Comparative Study of Task Adaptation Techniques of Large Language Models for Identifying Sustainable Development Goals 比较大型语言模型任务适应技术以识别可持续发展目标 large language model
12 FinEval-KR: A Financial Domain Evaluation Framework for Large Language Models' Knowledge and Reasoning 提出FinEval-KR框架以解决金融领域LLM评估问题 large language model
13 A General Method for Detecting Information Generated by Large Language Models 提出通用LLM检测器以解决信息生成识别问题 large language model
14 Hybrid EEG--Driven Brain--Computer Interface: A Large Language Model Framework for Personalized Language Rehabilitation 提出混合EEG驱动的脑机接口以解决个性化语言康复问题 large language model
15 Identifying economic narratives in large text corpora -- An integrated approach using Large Language Models 利用大型语言模型提取经济叙事以解决文本分析问题 large language model
16 Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning 提出单轮自我纠错机制以提升语言模型推理能力 large language model chain-of-thought
17 Understanding GUI Agent Localization Biases through Logit Sharpness 提出细粒度评估框架以解决GUI代理定位偏差问题 large language model multimodal
18 Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs 提出Graph RAG框架以解决历史文本分析中的知识缺口问题 large language model chain-of-thought
19 ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs 提出ProtoReasoning以解决大规模语言模型推理能力不足问题 large language model chain-of-thought
20 TokenShapley: Token Level Context Attribution with Shapley Value 提出TokenShapley以解决LLM生成响应的关键词归因问题 large language model
21 Veracity: An Open-Source AI Fact-Checking System 提出Veracity以应对虚假信息问题 large language model
22 Context-Informed Grounding Supervision 提出上下文信息引导监督以解决生成模型的基础问题 large language model
23 RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation 提出RE-IMAGINE框架以评估大型语言模型的推理能力 large language model
24 Rethinking LLM Training through Information Geometry and Quantum Metrics 通过信息几何与量子度量重新思考大语言模型训练 large language model
25 PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning 提出PhantomHunter以解决未见私有调优LLM生成文本检测问题 large language model
26 AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need 提出AgentGroupChat-V2以解决多智能体系统的复杂任务挑战 large language model ✅
27 PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights 提出PRAISE以解决电商产品描述不准确问题 large language model
28 SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture 提出SANSKRITI基准以评估语言模型对印度文化的理解 large language model
29 Lost in Variation? Evaluating NLI Performance in Basque and Spanish Geographical Variants 提出一种新数据集以评估巴斯克和西班牙语言变体的NLI性能 large language model
30 Mix-of-Language-Experts Architecture for Multilingual Programming 提出MoLE架构以解决多语言编程中的效率与专业化问题 large language model
31 Representation Consistency for Accurate and Coherent LLM Answer Aggregation 提出表示一致性方法以提升LLM答案聚合的准确性 large language model
32 Learning-Time Encoding Shapes Unlearning in LLMs 提出学习时间编码以解决大语言模型的去学习问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
33 CKD-EHR:Clinical Knowledge Distillation for Electronic Health Records 提出CKD-EHR框架以解决电子健康记录中的疾病预测效率问题 distillation large language model ✅
34 SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling 提出SPARE框架以解决自动过程注释效率低下问题 reinforcement learning offline reinforcement learning large language model
35 Lessons from Training Grounded LLMs with Verifiable Rewards 提出基于可验证奖励的强化学习方法以提升LLM的可信度 reinforcement learning distillation large language model
36 ConLID: Supervised Contrastive Learning for Low-Resource Language Identification 提出监督对比学习以解决低资源语言识别问题 contrastive learning
37 GenRecal: Generation after Recalibration from Large to Small Vision-Language Models 提出GenRecal以解决大规模视觉语言模型的蒸馏问题 distillation large language model
38 CC-LEARN: Cohort-based Consistency Learning 提出CC-Learn以提升大语言模型推理一致性 reinforcement learning large language model
39 Targeted Lexical Injection: Unlocking Latent Cross-Lingual Alignment in Lugha-Llama via Early-Layer LoRA Fine-Tuning 提出目标词汇注入方法以提升低资源语言模型的跨语言对齐能力 contrastive learning large language model
40 Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View 研究记忆机制，揭示Mamba模型中的首因与近因效应 Mamba

⬅️ 返回 cs.CL 首页 · 🏠 返回主页