cs.CL（2025-06-06）

📊 共 46 篇论文 | 🔗 11 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (37 🔗10) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (37 篇)

#题目一句话要点标签🔗⭐
1 SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language Capabilities 提出SMAR以解决多模态MoE模型语言能力下降问题 large language model multimodal
2 Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models 提出动态CoT方法以提高大语言模型推理效率 large language model chain-of-thought
3 PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts 提出PuzzleWorld基准以解决多模态开放式推理问题 foundation model multimodal ✅
4 MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems? 提出MATP-BENCH以评估多模态大语言模型在自动定理证明中的能力 large language model multimodal
5 LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles 提出LaMP-Cap以解决个性化图形标题生成问题 multimodal
6 Large Language Models are Good Relational Learners 提出Rel-LLM以解决关系深度学习中的结构化数据处理问题 large language model ✅
7 Beyond Facts: Evaluating Intent Hallucination in Large Language Models 提出FAITHQA基准以评估大型语言模型的意图幻觉问题 large language model
8 DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration 提出动态注意力掩码以加速长上下文大语言模型推理 large language model ✅
9 You Only Fine-tune Once: Many-Shot In-Context Fine-Tuning for Large Language Model 提出ManyICL以解决大语言模型微调效率低下问题 large language model
10 Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models 提出简单有效的提取攻击算法以解决联邦微调中的隐私数据风险 large language model
11 Hey, That's My Data! Label-Only Dataset Inference in Large Language Models 提出CatShift以解决大语言模型数据推断问题 large language model
12 Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefixing Improves Theory of Mind in Large Language Models 提出Shoes-of-Others前缀方法以提升大语言模型的心智理论能力 large language model
13 DynamicMind: A Tri-Mode Thinking System for Large Language Models 提出DynamicMind以解决大语言模型动态推理深度不足问题 large language model
14 MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models 提出异构适配器混合模型以解决参数高效微调问题 large language model ✅
15 RKEFino1: A Regulation Knowledge-Enhanced Large Language Model 提出RKEFino1以解决数字监管报告中的合规性挑战 large language model
16 Large Language Models are Demonstration Pre-Selectors for Themselves 提出FEEDER框架以提高大语言模型的示例选择效率 large language model
17 Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models 系统分类与分析大语言模型幻觉问题的解决方案 large language model
18 Elementary Math Word Problem Generation using Large Language Models 基于大型语言模型的数学文字题生成系统 large language model
19 Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Models 提出MEFA框架以解决事件因果关系识别中的数据依赖问题 large language model
20 Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs 提出DeBoP以优化轻量级大语言模型的行为 large language model chain-of-thought
21 Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance 提出TuluTalk数据集以提升LLM后训练性能 large language model instruction following
22 Can Theoretical Physics Research Benefit from Language Agents? 提出语言代理以加速理论物理研究的进展 large language model multimodal
23 IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems 提出IntentionESC框架以增强对话系统中的情感支持 large language model chain-of-thought ✅
24 BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions 提出BioMol-MQA以解决多模态生物分子交互问答问题 large language model multimodal
25 Canonical Autoregressive Generation 提出规范自回归生成方法以解决语言模型生成非规范序列问题 large language model
26 Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning 提出基于任务条件近似的零-shot检测方法以识别LLM生成代码 large language model ✅
27 Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights 识别价值对齐大型语言模型的安全风险以提升安全性 large language model
28 Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness 提出知识去学习评估框架以解决大语言模型遗忘问题 large language model ✅
29 When to Trust Context: Self-Reflective Debates for Context Reliability 提出自反辩论框架以提升上下文可靠性 large language model ✅
30 dots.llm1 Technical Report 提出dots.llm1以高效激活语言模型参数 large language model
31 Improving LLM-Powered EDA Assistants with RAFT 提出RAFT以提升LLM在EDA任务中的表现 large language model
32 Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge 提出DSSP-RAG以解决LLMs的幻觉问题 large language model
33 Detecting Voice Phishing with Precision: Fine-Tuning Small Language Models 通过微调小型语言模型提高语音钓鱼检测精度 chain-of-thought
34 Masked Language Models are Good Heterogeneous Graph Generalizers 提出MLM4HG以解决异构图泛化能力不足问题 large language model ✅
35 Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition 提出CONFER数据集以评估NLI模型在条件推理中的表现 large language model
36 AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search 提出AgentSwift以解决自动化代理设计中的高成本与低效率问题 large language model
37 When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation 提出GraphRAG-Bench以评估图检索增强生成的有效性 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
38 Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models 提出跨语言崩溃现象以揭示多语言模型推理的局限性 reinforcement learning reward shaping large language model
39 Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework 提出渐进式知识蒸馏框架以提升大语言模型性能 curriculum learning distillation large language model
40 Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router 提出R2-Reasoner以解决大规模语言模型推理效率问题 reinforcement learning large language model chain-of-thought
41 Unlocking Recursive Thinking of LLMs: Alignment via Refinement 提出AvR方法以提升大语言模型的递归推理能力 distillation large language model chain-of-thought ✅
42 Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning 提出Writing-RL框架以提升长篇写作能力 reinforcement learning large language model
43 Cartridges: Lightweight and general-purpose long context representations via self-study 提出Cartridges以解决长文本上下文处理的高成本问题 distillation large language model
44 Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach 提出多代理方法以降低文本到图表生成中的执行错误率 reinforcement learning large language model
45 Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning 通过执行反馈强化代码生成以提升文本到SQL的转换能力 reinforcement learning large language model
46 CodeContests+: High-Quality Test Case Generation for Competitive Programming 提出CodeContests+以解决竞争编程测试用例生成问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页