cs.CL（2025-06-05）

📊 共 61 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) (49 🔗10) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱一：机器人控制 (Robot Control) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (49 篇)

#题目一句话要点标签🔗⭐
1 MLLM-CL: Continual Learning for Multimodal Large Language Models 提出MLLM-CL以解决多模态大语言模型的持续学习问题 large language model multimodal ✅
2 MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models 提出MMRefine以解决多模态大语言模型的错误修正问题 large language model multimodal ✅
3 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification 提出Safe框架以解决大语言模型数学推理中的幻觉问题 large language model chain-of-thought
4 Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis 评估大型语言模型在金融情感分析中的有效性 large language model chain-of-thought
5 RELIC: Evaluating Compositional Instruction Following via Language Recognition 提出RELIC框架以评估语言识别中的指令遵循能力 large language model instruction following
6 Do Large Language Models Judge Error Severity Like Humans? 比较人类与大型语言模型在错误严重性判断上的差异 large language model multimodal
7 LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild Data 提出LESS框架以解决真实环境下语音模型的半监督学习挑战 large language model foundation model
8 Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models 提出约束熵消除方法以解决大语言模型遗忘问题 large language model
9 Does It Make Sense to Speak of Introspection in Large Language Models? 探讨大型语言模型中的内省概念及其局限性 large language model
10 Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights 利用大型语言模型生成多项选择题以解决教育评估问题 large language model
11 Fine-Grained Interpretation of Political Opinions in Large Language Models 提出四维政治学习框架以解决LLMs政治意见分析问题 large language model
12 Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models 提出Qwen3嵌入以提升文本嵌入和重排序能力 foundation model
13 SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View 提出SCOP以评估大型语言模型的理解过程 large language model
14 MuSciClaims: Multimodal Scientific Claim Verification 提出MuSciClaims以解决科学声明验证的多模态基准问题 multimodal
15 Parking, Perception, and Retail: Street-Level Determinants of Community Vitality in Harbin 提出图像基础框架以分析哈尔滨社区商业活力 large language model multimodal
16 The NTNU System at the S&I Challenge 2025 SLA Open Track 提出多模态融合系统以提升口语能力评估准确性 large language model multimodal
17 MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark 提出MMSU基准以解决多任务口语理解与推理问题 large language model multimodal ✅
18 TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering 提出TaDA以解决KV缓存压缩中的稀疏异常处理问题 large language model chain-of-thought
19 From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems 提出复合人工智能系统以解决独立模型的局限性 large language model multimodal
20 Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation 提出翻译自我修正方法以提升翻译质量 large language model chain-of-thought
21 ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development 提出ComfyUI-Copilot以解决ComfyUI使用中的挑战 large language model ✅
22 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets 通过相似性分析提出新方法以增强LLM安全性 large language model
23 Search Arena: Analyzing Search-Augmented LLMs 提出Search Arena以分析搜索增强型大语言模型的用户偏好 large language model ✅
24 ProRefine: Inference-Time Prompt Refinement with Textual Feedback 提出ProRefine以解决推理时提示优化问题 chain-of-thought
25 The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text 发布Common Pile v0.1数据集以解决LLM训练中的版权问题 large language model
26 Context Is Not Comprehension 提出Verbose ListOps基准以评估语言模型的推理能力 large language model
27 Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things 提出自然语言交互框架以解决战场物联网中的数据处理问题 large language model
28 Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation 提出动态上下文调优以解决多轮对话和工具适应问题 large language model
29 Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective 通过机械解释方法分析大型语言模型中的偏见 large language model
30 TALL -- A Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages 提出TALL以提升低资源语言的LLM性能 large language model
31 From Struggle (06-2024) to Mastery (02-2025) LLMs Conquer Advanced Algorithm Exams and Pave the Way for Editorial Generation 评估大型语言模型在高级算法考试中的表现与教育应用 large language model
32 Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback 提出多语言LLM辅导模拟以提升数学反馈效果 large language model
33 Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study 提出FineLogic框架以解决LLMs逻辑推理评估问题 large language model ✅
34 Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models 提出REWIRE方法以解决预训练数据质量和数量不足问题 large language model ✅
35 Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering 提出DMPI-PMHFE以解决提示注入攻击检测问题 large language model
36 Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs 提出输入依赖的软提示技术以提升大语言模型的微调效率 large language model
37 OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation 提出OPeRA数据集以解决LLMs模拟用户在线购物行为的挑战 large language model
38 SoK: Are Watermarks in LLMs Ready for Deployment? 提出水印系统化方法以解决LLMs部署中的知识产权风险 large language model
39 Improving LLMs with a knowledge from databases 提出基于增强关联规则的LLM知识改进方法 large language model
40 Just a Scratch: Enhancing LLM Capabilities for Self-harm Detection through Intent Differentiation and Emoji Interpretation 通过意图区分与表情符号解读提升自伤检测能力 large language model
41 Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers 提出AR-Checker以解决LLMs的鲁棒性测试问题 large language model
42 ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests 提出ICPC-Eval以解决LLM在编程竞赛中的评估问题 large language model ✅
43 Evaluating the Effectiveness of Linguistic Knowledge in Pretrained Language Models: A Case Study of Universal Dependencies 将通用依赖整合进预训练语言模型以提升跨语言任务性能 large language model
44 Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models 提出RACE框架以解决大型推理模型中的幻觉检测问题 large language model ✅
45 From Handwriting to Feedback: Evaluating VLMs and LLMs for AI-Powered Assessment in Indonesian Classrooms 评估VLM和LLM在印尼课堂AI评估中的应用 large language model
46 Identifying Reliable Evaluation Metrics for Scientific Text Revision 提出混合评估方法以解决科学文本修订评估问题 instruction following
47 A MISMATCHED Benchmark for Scientific Natural Language Inference 提出MISMATCHED基准以解决科学自然语言推理的领域偏差问题 large language model
48 Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching 提出梯度匹配方法以优化多示例上下文学习的演示选择 large language model
49 Are LLMs Stable Formal Logic Translators in Logical Reasoning Across Linguistically Diversified Texts? 提出SoLT和MenTaL以解决LLM逻辑推理中的符号不一致问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
50 Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniques 提出LLM中心的多模态融合框架以解决现有整合策略的不足 representation learning large language model multimodal
51 Customizing Speech Recognition Model with Large Language Model Feedback 提出基于大语言模型反馈的ASR模型定制方法以解决领域适应问题 reinforcement learning large language model
52 Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning 提出Tool-MVR以解决工具利用能力不足的问题 imitation learning large language model
53 RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation 提出RIVAL框架以解决口语字幕翻译中的奖励模型偏差问题 reinforcement learning RLHF large language model
54 Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models 提出自信强化学习方法以优化语言模型微调 reinforcement learning large language model
55 DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning 提出DiCoRe框架以增强零样本事件检测能力 dreamer large language model
56 Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement 提出Knowledgeable-R1以解决RAG中的上下文干扰问题 reinforcement learning large language model ✅
57 Static Word Embeddings for Sentence Semantic Representation 提出静态词嵌入以优化句子语义表示 contrastive learning distillation

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
58 CL-ISR: A Contrastive Learning and Implicit Stance Reasoning Framework for Misleading Text Detection on Social Media 提出CL-ISR框架以解决社交媒体误导文本检测问题 manipulation contrastive learning
59 Normative Conflicts and Shallow AI Alignment 探讨LLM的规范冲突与浅层AI对齐问题 manipulation large language model
60 Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning 提出ADAPT方法以解决推理多样性不足问题 trajectory optimization large language model
61 Demonstrations of Integrity Attacks in Multi-Agent Systems 探讨多智能体系统中的完整性攻击及其防范 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页