cs.CL（2025-05-26）

📊 共 67 篇论文 | 🔗 12 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (52 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (14 🔗5) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (52 篇)

#题目一句话要点标签🔗⭐
1 Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction 提出视觉抽象思维以提升多模态推理能力 large language model multimodal chain-of-thought
2 SEMMA: A Semantic Aware Knowledge Graph Foundation Model 提出SEMMA以解决知识图谱推理中的语义不足问题 large language model foundation model
3 WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback 提出WebCoT以增强网络代理在动态环境中的推理能力 large language model chain-of-thought
4 ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs 提出ALAS以解决多模态LLMs中的语音文本对齐问题 large language model multimodal
5 MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding 提出MangaVQA和MangaLMM以解决多模态漫画理解问题 multimodal
6 MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks 提出MedHELM框架以全面评估医疗任务中的大型语言模型表现 large language model
7 Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableism 评估大型语言模型对细微能力歧视的分类能力 large language model
8 Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects 提出多模态情感识别方法以解决对话系统情感理解不足的问题 multimodal
9 Large Language Models for IT Automation Tasks: Are We There Yet? 提出ITAB基准以评估LLM在IT自动化任务中的表现 large language model
10 WXImpactBench: A Disruptive Weather Impact Understanding Benchmark for Evaluating Large Language Models 提出WXImpactBench以评估大语言模型在极端天气影响理解中的能力 large language model
11 THiNK: Can Large Language Models Think-aloud? 提出THiNK框架以评估大型语言模型的高阶思维能力 large language model
12 Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers 提出EXSEARCH框架以解决LLM在复杂任务中的信息检索问题 large language model
13 ResSVD: Residual Compensated SVD for Large Language Model Compression 提出ResSVD以解决大语言模型压缩中的残差损失问题 large language model
14 Language-Agnostic Suicidal Risk Detection Using Large Language Models 提出语言无关的自杀风险检测框架以解决现有方法局限性 large language model
15 Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities 提出知识图谱与大语言模型结合的方法以解决复杂问答问题 large language model
16 MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning 提出MA-RAG框架以解决复杂信息检索中的推理挑战 chain-of-thought
17 MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models 提出MiniLongBench以降低长文本理解基准的评估成本 large language model ✅
18 FoodTaxo: Generating Food Taxonomies with Large Language Models 提出FoodTaxo以解决食品技术领域分类生成问题 large language model
19 T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search 提出T^2Agent以解决多模态虚假信息检测问题 multimodal
20 Reasoning LLMs are Wandering Solution Explorers 提出系统性问题解决框架以提升推理LLM的探索能力 large language model chain-of-thought
21 MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents 提出MemGuide以解决多会话对话系统中的意图驱动记忆选择问题 large language model chain-of-thought
22 OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction 提出OmniCharacter以解决角色扮演代理的语音与语言互动问题 large language model ✅
23 SelfReflect: Can LLMs Communicate Their Internal Answer Distribution? 提出SelfReflect以揭示大型语言模型的不确定性 large language model
24 Does quantization affect models' performance on long-context tasks? 系统评估量化对长上下文任务的影响 large language model
25 Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline 提出向量干预以解决多语言事实回忆不一致问题 large language model
26 Gatsby Without the 'E': Crafting Lipograms with LLMs 利用大型语言模型生成无'e'的文本 large language model
27 Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries 提出Amulet框架以提升复杂多轮对话的LLM评估能力 large language model
28 HAMburger: Accelerating LLM Inference via Token Smashing 提出HAMburger以加速大语言模型推理效率 large language model
29 Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery 提出ECO-Concept以解决文本解释的可理解性问题 large language model
30 FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models 提出FLAME-MoE以解决现有MoE语言模型研究平台不足问题 large language model ✅
31 Estimating LLM Consistency: A User Baseline vs Surrogate Metrics 提出基于logit的集成方法以评估LLM一致性 large language model
32 How to Improve the Robustness of Closed-Source Models on NLI 提出数据中心方法以提升闭源模型在NLI任务中的鲁棒性 large language model
33 Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations 提出MedAgent框架以解决多轮心理健康对话评估问题 large language model
34 Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs 提出Pangu Light以解决大语言模型压缩与加速问题 large language model
35 UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models 提出UORA以实现大模型的高效微调 large language model
36 Semantic-Preserving Adversarial Attacks on LLMs: An Adaptive Greedy Binary Search Approach 提出自适应贪婪二分搜索方法以解决LLMs的语义保持对抗攻击问题 large language model ✅
37 TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent 提出TrojanStego以解决语言模型隐私泄露问题 large language model
38 Named Entity Recognition in Historical Italian: The Case of Giacomo Leopardi's Zibaldone 提出新数据集以解决历史意大利文本命名实体识别问题 large language model
39 Multi-Domain Explainability of Preferences 提出一种自动化方法以实现多领域偏好解释 large language model
40 Inference-time Alignment in Continuous Space 提出简单能量适应算法以解决推理时对齐问题 large language model ✅
41 Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks 提出概率上下文无关文法以解决LLM在自动推理中的不确定性问题 large language model
42 Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking 提出STeP方法以解决LLM代理训练中的性能瓶颈问题 large language model
43 Emergent LLM behaviors are observationally equivalent to data leakage 揭示大型语言模型行为与数据泄露的关系 large language model
44 DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset 提出DeepDialogue以解决多轮对话情感表达不足问题 multimodal
45 APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation 提出APE方法以解决语言模型适应性问题 large language model
46 Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages 评估大型语言模型在印度语言音译中的表现 large language model
47 Improving Multilingual Math Reasoning for African Languages 提出多阶段适应策略以改善非洲语言的数学推理能力 large language model
48 Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective 提出一种新框架以优化大语言模型的推理能力 large language model
49 Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks 系统性探讨大型语言模型中的意识理论与风险 large language model ✅
50 MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs 提出MOLE框架以自动提取科学论文中的元数据 large language model ✅
51 What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs 研究长上下文漏洞，揭示LLM安全机制的不足 large language model
52 SGM: A Framework for Building Specification-Guided Moderation Filters 提出SGM框架以解决内容审核中的对齐问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
53 Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models 提出MARA方法以解决大语言模型对齐效率低下问题 preference learning RLHF DPO ✅
54 Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles 提出Enigmata以提升大语言模型的逻辑推理能力 reinforcement learning large language model
55 MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning 提出MT³框架以解决文本图像机器翻译中的多任务挑战 reinforcement learning large language model multimodal
56 MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability 提出MaskSearch框架以增强智能搜索能力 reinforcement learning curriculum learning distillation
57 Adaptive Deep Reasoning: Triggering Deep Thinking When Needed 提出自适应深度推理以解决计算成本高的问题 reinforcement learning large language model chain-of-thought
58 Incentivizing Strong Reasoning from Weak Supervision 提出弱监督激励强推理以提升大语言模型推理能力 reinforcement learning large language model chain-of-thought ✅
59 REARANK: Reasoning Re-ranking Agent via Reinforcement Learning 提出REARANK以提升信息检索中的重排序性能 reinforcement learning large language model
60 Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation 提出选择性推理蒸馏以提升心理疾病检测效果 distillation large language model
61 R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning 提出R3-RAG以解决RAG系统中的推理与检索瓶颈问题 reinforcement learning large language model ✅
62 Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision 通过符号引导的蒙特卡洛过程监督提升语言模型的逻辑推理能力 DPO direct preference optimization large language model
63 One-shot Entropy Minimization 提出单次熵最小化方法以提升大语言模型性能 reinforcement learning large language model ✅
64 Efficient Speech Translation through Model Compression and Knowledge Distillation 通过模型压缩与知识蒸馏提高语音翻译效率 distillation
65 Token Distillation: Attention-aware Input Embeddings For New Tokens 提出Token Distillation以快速学习新词的高质量嵌入 distillation
66 REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Large Reasoning Models 提出REA-RL以解决大型推理模型的高推理成本问题 reinforcement learning ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
67 Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking 提出自适应无分类器引导以解决生成模型中的不确定性问题 classifier-free guidance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页