cs.CL（2025-05-20）

📊 共 109 篇论文 | 🔗 15 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (83 🔗12) 支柱二：RL算法与架构 (RL & Architecture) (24 🔗3) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (83 篇)

#题目一句话要点标签🔗⭐
1 Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs 提出内部思维链以提升大语言模型的任务执行透明度 large language model chain-of-thought
2 ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models 提出ABBA以解决大语言模型高效适应新领域的问题 large language model foundation model ✅
3 EfficientLLM: Efficiency in Large Language Models 提出EfficientLLM以解决大语言模型效率问题 large language model foundation model
4 ModRWKV: Transformer Multimodality in Linear Time 提出ModRWKV以解决多模态学习中的计算复杂性问题 large language model multimodal
5 Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales 提出LRSA框架以解决多模态情感分析中的信息整合问题 large language model multimodal
6 CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring 提出CAFES框架以解决多模态自动作文评分问题 large language model multimodal
7 DecIF: Improving Instruction-Following through Meta-Decomposition 提出DecIF框架以解决指令跟随数据生成的灵活性问题 large language model instruction following
8 Large Language Models Implicitly Learn to See and Hear Just By Reading 提出通过文本训练实现视觉与听觉理解的长语言模型 large language model
9 Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models 提出Saten以解决大语言模型压缩问题 large language model
10 Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning 提出N-rep一致性以降低文本到SQL转换成本 chain-of-thought
11 Scaling Laws for State Dynamics in Large Language Models 探讨大语言模型状态动态的规模法则 large language model
12 Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models 提出TruthHypo与KnowHD以解决科学假设生成的真实性问题 large language model ✅
13 Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations 提出SDA框架以解决代码混合下LLM的安全性问题 large language model
14 Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models 提出LaTen以解决大规模语言模型间知识转移问题 large language model ✅
15 DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models 提出DiagnosisArena以评估大型语言模型的诊断推理能力 large language model ✅
16 Development and Validation of Engagement and Rapport Scales for Evaluating User Experience in Multimodal Dialogue Systems 提出用户体验评估量表以优化多模态对话系统 multimodal
17 Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies 提出CROSS基准以评估大型视觉语言模型的文化安全性 multimodal
18 DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis 提出DECASTE框架以揭示大语言模型中的种姓偏见 large language model
19 Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples 提出LISTEN以解决音频感知大语言模型的幻觉问题 large language model
20 S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models 提出S2SBench以量化语音到语音大语言模型的智能退化问题 large language model ✅
21 OmniGenBench: A Modular Platform for Reproducible Genomic Foundation Models Benchmarking 提出OmniGenBench以解决基因组基础模型评估的可重复性问题 foundation model
22 QA-prompting: Improving Summarization with Large Language Models using Question-Answering 提出QA-prompting以解决长文本摘要中的位置信息偏差问题 large language model
23 Cross-Lingual Optimization for Language Transfer in Large Language Models 提出跨语言优化方法以解决大语言模型语言迁移问题 large language model
24 Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification 提出统一框架分析大语言模型在作者隐私中的作用 large language model
25 Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering 提出PDRR框架以解决复杂问答中的知识库整合问题 large language model
26 ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 提出ShieldVLM以解决多模态隐性毒性检测问题 multimodal
27 AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation 提出AutoLaw以解决法律合规性问题 large language model
28 Activation-Guided Consensus Merging for Large Language Models 提出激活引导共识合并以提升大语言模型的效率与稳定性 large language model
29 Mixed Signals: Understanding Model Disagreement in Multimodal Empathy Detection 提出多模态模型以解决同类信号冲突问题 multimodal
30 Informatics for Food Processing 提出FoodProX模型以解决食品加工分类的主观性问题 large language model multimodal
31 Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese 提出Amadeus Verbo模型以促进巴西葡萄牙语的开放源代码发展 large language model foundation model ✅
32 PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs 提出PersonaTAB以解决个性化对话系统缺乏个性标注的问题 large language model TAMP
33 Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst 提出自推理语言模型以提升复杂推理任务的性能 large language model chain-of-thought
34 Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM 提出图基分析框架以提升大语言模型推理能力 large language model chain-of-thought
35 Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels 提出TLDM基准以评估LLM在长上下文理解中的表现 large language model
36 EasyMath: A 0-shot Math Benchmark for SLMs 提出EasyMath基准以评估小型语言模型的数学推理能力 chain-of-thought
37 Automated Journalistic Questions: A New Method for Extracting 5W1H in French 提出自动化提取法以解决法语新闻5W1H信息提取问题 large language model
38 UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models 提出UltraEdit以解决大规模语言模型的终身编辑问题 large language model ✅
39 WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications 提出WirelessMathBench以评估LLMs在无线通信中的数学建模能力 large language model
40 Temporal Alignment of Time Sensitive Facts with Activation Engineering 提出激活工程以解决大语言模型的时间敏感性问题 large language model
41 Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability 研究量化对大语言模型可解释性与可理解性的影响 large language model
42 Mechanistic Interpretability of GPT-like Models on Summarization Tasks 提出机制可解释性框架以分析GPT模型在摘要任务中的表现 large language model
43 WebNovelBench: Placing LLM Novelists on the Web Novel Distribution 提出WebNovelBench以解决长篇小说生成评估问题 large language model
44 Creative Preference Optimization 提出创意偏好优化方法以提升LLM的创造力 large language model
45 MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language 提出MUG-Eval框架以评估多语言生成能力 large language model
46 GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data 提出GemMaroc以解决摩洛哥阿拉伯语处理问题 large language model
47 Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits 提出Token Awareness以解决LLMs中的符号推理限制问题 chain-of-thought
48 A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations 提出PersonaConvBench以评估个性化对话生成能力 large language model
49 GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace 提出GloSS以解决大语言模型中的毒性问题 large language model
50 From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora 提出多路平行语料库以提升多语言大模型性能 large language model
51 FlashThink: An Early Exit Method For Efficient Reasoning 提出FlashThink以解决大语言模型推理效率问题 large language model
52 EEG-to-Text Translation: A Model for Deciphering Human Brain Activity 提出R1 Translator以提升脑电图到文本翻译性能 large language model ✅
53 ConspEmoLLM-v2: A robust and stable model to detect sentiment-transformed conspiracy theories 提出ConspEmoLLM-v2以解决情感转变阴谋论检测问题 large language model ✅
54 Concept Incongruence: An Exploration of Time and Death in Role Playing 提出概念不一致性以分析角色扮演中的时间与死亡问题 large language model
55 Incorporating Token Usage into Prompting Strategy Evaluation 提出Big-$O_{tok}$框架以优化提示策略的效率评估 large language model
56 SEPS: A Separability Measure for Robust Unlearning in LLMs 提出SEPS框架以解决大语言模型的混合查询遗忘问题 large language model
57 Tracing Multilingual Factual Knowledge Acquisition in Pretraining 追踪多语言事实知识获取以提升语言模型的跨语言一致性 large language model ✅
58 Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes 系统研究语言混合对推理语言模型的影响及优化策略 chain-of-thought
59 sudoLLM: On Multi-role Alignment of Language Models 提出sudoLLM以解决语言模型的多角色对齐问题 large language model
60 TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring 提出TRATES以解决个体特征评估不足的问题 large language model
61 Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders 利用稀疏自编码器实现大型语言模型的去毒化 large language model
62 MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance 提出MoMoE框架以解决在线社区内容审核透明性问题 large language model
63 Rank-K: Test-Time Reasoning for Listwise Reranking 提出Rank-K以解决多语言查询的高效重排序问题 large language model
64 From Templates to Natural Language: Generalization Challenges in Instruction-Tuned LLMs for Spatial Reasoning 研究空间推理中的指令泛化挑战 large language model
65 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis 提出PhantomCircuit以解决知识遮蔽问题 large language model
66 Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs 提出有效的提示注入攻击以评估开源LLM的安全性 large language model
67 Dual Decomposition of Weights and Singular Value Low Rank Adaptation 提出DuDe以解决LoRA方法的训练不稳定和知识转移效率低的问题 large language model
68 OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation 提出OSoRA以解决大规模语言模型微调的计算资源挑战 large language model
69 Teaching Small Language Models to Learn Logic through Meta-Learning 通过元学习提升小型语言模型的逻辑推理能力 large language model
70 JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling 提出JOLT-SQL以解决文本到SQL映射中的噪声模式问题 large language model ✅
71 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs 提出通用声学对抗攻击以灵活控制语音大语言模型 large language model
72 ThinkSwitcher: When to Think Hard, When to Think Fast 提出ThinkSwitcher以解决大规模推理模型的计算效率问题 chain-of-thought
73 SlangDIT: Benchmarking LLMs in Interpretative Slang Translation 提出SlangDIT以解决俚语翻译中的语境依赖问题 large language model
74 The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Models 提出轻量级架构改进以解决字符级理解问题 large language model
75 Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents 提出法律规则诱导方法以解决从判例中提取隐性原则的问题 large language model
76 MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations 提出MultiHal以解决多语言知识图谱基础的LLM幻觉评估问题 large language model
77 BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks 提出BAR代理以解决复杂Minecraft任务中的推理问题 large language model
78 Enhancing LLMs via High-Knowledge Data Selection 提出高知识评分器以解决LLMs知识稀缺问题 large language model
79 Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation 提出多模态检索增强生成的隐私漏洞分析方法 multimodal
80 Cross-Linguistic Transfer in Multilingual NLP: The Role of Language Families and Morphology 探讨语言家族与形态学在多语言NLP中的跨语言迁移作用 zero-shot transfer
81 Let's Verify Math Questions Step by Step 提出MathQ-Verify以解决数学问题验证的挑战 large language model ✅
82 PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks 提出PandaGuard以系统评估LLM安全性应对越狱攻击 large language model
83 Improve Language Model and Brain Alignment via Associative Memory 通过联想记忆提升语言模型与大脑的对齐 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (24 篇)

#题目一句话要点标签🔗⭐
84 Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models 提出MathIF基准以评估大规模推理模型的指令遵循能力 reinforcement learning large language model instruction following ✅
85 Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning 提出CoT思想跃迁桥接任务以解决数学推理中的中间步骤缺失问题 reinforcement learning large language model chain-of-thought
86 Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models 提出强化学习微调方法以提升医学视觉问答性能 reinforcement learning large language model multimodal
87 FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation 提出FuxiMT以解决中文为中心的多语言机器翻译问题 curriculum learning large language model
88 Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning 提出Game-RL以提升视觉语言模型的推理能力 reinforcement learning multimodal
89 Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation 提出基于规则分解的知识蒸馏方法以提升小型语言模型的可解释性 distillation chain-of-thought
90 Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning 提出Mujica-MyGo框架以解决长上下文问题 reinforcement learning large language model
91 Reward Reasoning Model 提出奖励推理模型以提升奖励模型性能 reinforcement learning large language model chain-of-thought ✅
92 General-Reasoner: Advancing LLM Reasoning Across All Domains 提出General-Reasoner以解决LLM推理能力不足问题 reinforcement learning large language model chain-of-thought
93 Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning 提出Context Reasoner以解决LLMs的隐私与安全合规问题 reinforcement learning large language model
94 Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents 提出AgentGhost以解决MLLM驱动的GUI代理后门攻击问题 contrastive learning large language model multimodal
95 Improved Methods for Model Pruning and Knowledge Distillation 提出MAMA剪枝方法以解决模型剪枝性能下降问题 distillation large language model
96 InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion 提出InfiGFusion以解决异构模型融合中的语义依赖问题 distillation large language model
97 Think-J: Learning to Think for Generative LLM-as-a-Judge 提出Think-J以提升生成式LLM的评判能力 reinforcement learning offline RL large language model
98 KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation 提出KORGym以解决LLM推理评估的不足问题 reinforcement learning large language model
99 Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation 提出日志增强生成框架以提升模型推理能力 distillation large language model
100 Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency 提出LAPS-SD以解决LLM推理延迟问题 SSM large language model
101 Think Only When You Need with Large Hybrid-Reasoning Models 提出大型混合推理模型以提高推理效率和准确性 reinforcement learning large language model
102 Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning 提出Prune-on-Logic框架以提升长链思维推理效果 distillation chain-of-thought
103 Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning 提出Citss框架以解决学术引用分类中的数据稀缺问题 contrastive learning
104 Not All Correct Answers Are Equal: Why Your Distillation Source Matters 通过高质量蒸馏数据提升语言模型推理能力 distillation ✅
105 FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning 提出FAID框架以解决AI生成文本的细粒度检测问题 contrastive learning
106 DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models 提出DRP以解决大型推理模型的效率问题 distillation chain-of-thought
107 Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals 提出优化模型选择方法以提高LLM反事实评估的可靠性 distillation large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
108 Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models 提出对抗场景外推方法以增强语言模型的鲁棒性 ASE large language model chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
109 Not Minds, but Signs: Reframing LLMs through Semiotics 通过符号学视角重构大型语言模型的理解方式 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页