cs.CL（2025-08-04）

📊 共 37 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (33 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (33 篇)

#题目一句话要点标签🔗⭐
1 Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models 提出一致性多模态推理框架以解决复杂推理问题 large language model multimodal
2 XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs 提出XFacta以解决多模态虚假信息检测的评估问题 large language model multimodal
3 Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time 提出STIM框架以诊断链式思维推理中的记忆化问题 large language model chain-of-thought
4 TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models 提出TIBSTC-CoT以解决藏语数据稀缺问题 large language model chain-of-thought ✅
5 Semantic Structure in Large Language Model Embeddings 揭示大型语言模型嵌入中的语义结构以优化特征引导 large language model
6 MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification 提出MArgE框架以解决多LLM证据整合问题 large language model
7 From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks 研究语言条件对大型语言模型心理语言学任务的影响 large language model
8 AI-Based Measurement of Innovation: Mapping Expert Insight into Large Language Model Applications 提出基于大语言模型的创新测量框架以解决专家评估局限性 large language model
9 Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models 提出PNLAC与InhibitFT以解决政治立场跨主题泛化问题 large language model
10 Isolating Culture Neurons in Multilingual Large Language Models 提出一种方法以识别多语言大语言模型中的文化神经元 large language model ✅
11 When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models 揭示大型语言模型中谄媚行为的内在机制 large language model
12 Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in Large Language Models 提出TDBench以解决时间敏感问答评估的局限性 large language model ✅
13 Prompting Large Language Models to Detect Dementia Family Caregivers 提出基于大语言模型的推文检测方法以支持痴呆症家庭护理者 large language model
14 Clinically Grounded Agent-based Report Evaluation: An Interpretable Metric for Radiology Report Generation 提出ICARE框架以解决放射科报告生成的评估问题 large language model foundation model
15 PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs 提出PoeTone框架以实现结构化中文宋词的约束生成 large language model chain-of-thought
16 Can LLMs Generate High-Quality Task-Specific Conversations? 提出参数化框架以控制大语言模型对话质量 large language model
17 Test Set Quality in Multilingual LLM Evaluation 提出多语言LLM评估数据集质量分析方法以提升评估准确性 large language model
18 AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification 提出AutoGeTS以解决文本分类数据不足问题 large language model
19 Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs 提出新分类法以分析大语言模型中的记忆现象 large language model
20 Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction 提出Sparse-dLLM以解决扩散大语言模型的计算复杂性问题 large language model ✅
21 I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2 揭示LLaMA 3.2内部音素表示以提升韵律任务能力 large language model
22 Modular Arithmetic: Language Models Solve Math Digit by Digit 提出数字位置特定电路以解决语言模型的算术问题 large language model
23 Monsoon Uprising in Bangladesh: How Facebook Shaped Collective Identity 研究Facebook在孟加拉国集体身份构建中的作用 multimodal
24 CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation 提出CompressKV以解决长上下文处理中的KV缓存效率问题 large language model ✅
25 CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis 提出CAMERA框架以解决MoE模型的冗余压缩问题 large language model
26 VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo 提出VeOmni以解决多模态大模型训练效率低下问题 large language model
27 LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training 提出LaMPE以解决长文本输入的性能下降问题 large language model ✅
28 Proof2Hybrid: Automatic Mathematical Benchmark Synthesis for Proof-Centric Problems 提出Proof2Hybrid以解决数学基准测试自动生成问题 large language model
29 Learning Dynamics of Meta-Learning in Small Model Pretraining 提出元学习动态以优化小模型预训练 large language model
30 Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers 提出HIN框架以揭示音频大语言模型中的后门攻击问题 large language model
31 Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions 提出FiqhQA基准以评估LLM在宗教问题上的可靠性与回避行为 large language model
32 The SMeL Test: A simple benchmark for media literacy in language models 提出SMeL测试以评估语言模型的媒体素养能力 large language model
33 SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents 构建SpeechRole数据集以评估语音角色扮演代理的性能 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
34 Mitigating Attention Hacking in Preference-Based Reward Modeling via Interaction Distillation 提出交互蒸馏以解决偏好奖励建模中的注意力劫持问题 reinforcement learning RLHF distillation
35 Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning 提出动态调整奖励信号的方法以优化强化学习效果 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
36 DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing 提出DINA框架以应对NLP中的内部噪声和外部攻击问题 manipulation large language model
37 Marco-Voice Technical Report 提出Marco-Voice以解决自然语音合成中的情感控制问题 manipulation contrastive learning ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页