cs.CL（2025-06-11）

📊 共 56 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (41 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (14 🔗3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (41 篇)

#题目一句话要点标签🔗⭐
1 Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings 评估大型语言模型在多模态环境中的欺骗检测能力 large language model multimodal chain-of-thought
2 Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning 提出因果框架以提升链式思维推理能力 large language model chain-of-thought
3 Debunk and Infer: Multimodal Fake News Detection via Diffusion-Generated Evidence and LLM Reasoning 提出Debunk-and-Infer框架以解决假新闻检测问题 large language model multimodal
4 VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented Generation 提出VAT-KG以解决多模态知识图谱的知识覆盖不足问题 large language model multimodal
5 Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting 提出改进的监督微调方法以缓解灾难性遗忘问题 large language model instruction following
6 Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models 基于配对大语言模型的困惑度检测阿尔茨海默病 large language model instruction following
7 When Large Language Models are Reliable for Judging Empathic Communication 评估大型语言模型在同理沟通判断中的可靠性 large language model
8 Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages 利用大型语言模型检测低资源巴尔干语言中的有毒语言 large language model
9 CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios 提出CRITICTOOL以评估大型语言模型在工具调用错误场景中的自我批评能力 large language model ✅
10 The Emergence of Abstract Thought in Large Language Models Beyond Any Language 提出语言无关参数空间以支持大型语言模型的抽象思维 large language model
11 Continuously Updating Digital Twins using Large Language Models 提出CALM-DT以解决数字双胞胎更新问题 large language model
12 Query-Level Uncertainty in Large Language Models 提出查询级不确定性方法以提升大语言模型的知识边界识别 large language model
13 From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies 探讨知识图谱与大语言模型的协同以提升推理能力 large language model
14 MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions 提出MEDUSA框架以解决自然条件下的语音情感识别问题 multimodal
15 Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models 提出Token约束解码以提升大语言模型的问答鲁棒性 large language model
16 DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts 提出DIVE方法以增强大语言模型的多样性重建 large language model
17 DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations 提出DrVoice以解决语音生成中的模态不一致问题 large language model foundation model
18 Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval 提出Q2E方法以解决零样本多语言文本到视频检索问题 multimodal
19 When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs 提出PBSS框架以评估LLMs在语义等价提示下的行为漂移 large language model
20 Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information 提出Chat-of-Thought以解决工业资产FMEA文档生成问题 large language model
21 A quantum semantic framework for natural language processing 提出量子语义框架以解决自然语言处理中的语义退化问题 large language model
22 TaskCraft: Automated Generation of Agentic Tasks 提出TaskCraft以解决现有代理任务生成的不足问题 foundation model
23 Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs 提出逐步指令与简化表格格式以提升LLM的依存解析准确性 large language model
24 GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations 提出GraphLAMA以解决图语言模型适应性不足问题 large language model
25 Bench to the Future: A Pastcasting Benchmark for Forecasting Agents 提出BTF基准以解决预测代理评估问题 chain-of-thought
26 PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants 提出PersonaLens以解决个性化评估在对话AI助手中的挑战 large language model
27 Attention Head Embeddings with Trainable Deep Kernels for Hallucination Detection in LLMs 提出基于可训练深度核的注意力头嵌入以检测LLM中的幻觉 large language model
28 AI shares emotion with humans across languages and cultures 提出情感调控方法以增强人机情感交流 large language model
29 Do LLMs Give Psychometrically Plausible Responses in Educational Assessments? 评估大型语言模型在教育评估中的心理测量合理性 large language model
30 Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models 提出Inv-Entropy框架以量化语言模型的不确定性 large language model ✅
31 Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Data 提出Fine-Tuning方法以解决无结构知识编辑的局限性 large language model
32 Benchmarking Debiasing Methods for LLM-based Parameter Estimates 比较LLM基础参数估计的去偏方法以解决偏差问题 large language model
33 Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language 提出马其顿开放基础语言模型及语料库以解决低资源语言问题 large language model
34 Can LLMs Reason About Trust?: A Pilot Study 探讨大型语言模型在信任推理中的应用 large language model
35 Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference 提出LayerCast以解决LLM推理中的数值不确定性问题 large language model ✅
36 ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment Framework 提出ASP2LJ框架以解决法律判决预测中的长尾分布和律师作用不足问题 large language model
37 UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs 提出UniToMBench以提升大型语言模型的心智理论能力 large language model ✅
38 GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture 提出GigaChat家族以高效建模俄语语言 large language model ✅
39 Comparing human and LLM politeness strategies in free production 比较人类与大型语言模型的礼貌策略以解决对齐挑战 large language model
40 Taming SQL Complexity: LLM-Based Equivalence Evaluation for Text-to-SQL 提出基于LLM的SQL等价评估方法以解决文本到SQL转换中的复杂性问题 large language model
41 ScholarSearch: Benchmarking Scholar Searching Ability of LLMs 提出ScholarSearch以解决学术搜索能力评估问题 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🔗⭐
42 Reinforcement learning fine-tuning of language model for instruction following and math reasoning 通过强化学习微调语言模型以提升指令跟随和数学推理能力 reinforcement learning DPO direct preference optimization
43 VerIF: Verification Engineering for Reinforcement Learning in Instruction Following 提出VerIF以解决指令跟随中的强化学习验证问题 reinforcement learning large language model instruction following ✅
44 Towards Efficient and Effective Alignment of Large Language Models 提出Lion和WebR以提升大语言模型的对齐效率与效果 DPO direct preference optimization distillation
45 Classifying Unreliable Narrators with Large Language Models 提出使用计算方法识别不可靠叙述者以解决文本可信度问题 curriculum learning large language model
46 GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models 提出GenBreak框架以评估文本生成图像模型的安全性 reinforcement learning large language model
47 Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms 提出POET以解决直接对齐算法中的奖励生成差距问题 reinforcement learning RLHF DPO
48 ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering 提出ChartReasoner以解决图表问答中的视觉推理问题 reinforcement learning large language model multimodal
49 TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding 提出TransXSSM以解决Transformer与状态空间模型的编码不兼容问题 SSM state space model
50 ComfyUI-R1: Exploring Reasoning Models for Workflow Generation 提出ComfyUI-R1以解决自动化工作流生成的挑战 reinforcement learning chain-of-thought
51 Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective 提出基于叙事规划的基准以评估LLMs的故事生成能力 reinforcement learning large language model
52 From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring 提出流式内容监控以解决LLM有害输出的早期停止问题 DPO large language model
53 CoRT: Code-integrated Reasoning within Thinking 提出CoRT框架以提升大规模推理模型的数学运算能力 reinforcement learning chain-of-thought ✅
54 RePO: Replay-Enhanced Policy Optimization 提出Replay-Enhanced Policy Optimization以解决RL数据效率低下问题 reinforcement learning large language model ✅
55 Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation 提出多智能体语言模型以增强合作与适应能力 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
56 Dataset of News Articles with Provenance Metadata for Media Relevance Assessment 提出新闻媒体来源数据集以解决媒体相关性评估问题 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页