cs.CL（2025-08-19）

📊 共 34 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (28 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (28 篇)

#题目一句话要点标签🔗⭐
1 MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models 提出MME-SCI以解决多模态大语言模型评估中的关键挑战 large language model multimodal ✅
2 CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation 提出CyPortQA以解决港口飓风应对中的多模态数据整合问题 large language model multimodal
3 Generics and Default Reasoning in Large Language Models 评估大型语言模型在默认推理中的表现与局限性 large language model chain-of-thought
4 Can Large Language Models (LLMs) Describe Pictures Like Children? A Comparative Corpus Study 比较大型语言模型与儿童语言描述的相似性 large language model multimodal
5 Mechanistic Exploration of Backdoored Large Language Model Attention Patterns 探讨后门攻击对大型语言模型注意力模式的影响 large language model
6 A Review of Developmental Interpretability in Large Language Models 综述大型语言模型的开发性可解释性研究进展 large language model
7 ViExam: Are Vision Language Models Better than Humans on Vietnamese Multimodal Exam Questions? 提出ViExam基准以评估视觉语言模型在越南多模态考试中的表现 multimodal
8 Ask Good Questions for Large Language Models 提出Ask-Good-Question框架以解决对话系统中的用户困惑问题 large language model
9 ALIGN: Word Association Learning for Cultural Alignment in Large Language Models 提出ALIGN方法以解决大型语言模型的文化偏见问题 large language model
10 The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities 利用大型语言模型解决数字健康领域情感分析挑战 large language model
11 MATA (māta): Mindful Assessment of the Telugu Abilities of Large Language Models 提出MATA评估数据集以评估大型语言模型的泰卢固语能力 large language model
12 Scalable Scientific Interest Profiling Using Large Language Models 提出基于大语言模型的科学兴趣画像生成方法 large language model
13 Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation 提出LoRA微调方法以解决阿拉伯方言生成问题 large language model foundation model
14 Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs 提出基于提示的一次性精确长度控制生成方法以解决LLMs文本生成问题 large language model instruction following
15 MultiFuzz: A Dense Retrieval-based Multi-Agent System for Network Protocol Fuzzing 提出MultiFuzz以解决传统协议模糊测试的有效性问题 large language model chain-of-thought
16 Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA 提出Pressure-Tune以解决科学问答中的谄媚偏见问题 large language model chain-of-thought
17 Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency 提出Finch-Zk以解决大型语言模型的幻觉检测与缓解问题 large language model
18 GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs 提出GRILE基准以解决罗马尼亚LLMs的语法推理与解释问题 large language model
19 Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text 提出DA-MTL框架以解决LLM生成文本的检测与归属问题 large language model
20 Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation 提出PING方法以解决大语言模型的安全性问题 large language model
21 DPad: Efficient Diffusion Language Models with Suffix Dropout 提出DPad以解决扩散语言模型的计算效率问题 large language model ✅
22 Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings 挑战传统假设，揭示词嵌入的解释能力局限性 large language model
23 Alvorada-Bench: Can Language Models Solve Brazilian University Entrance Exams? 提出Alvorada-Bench以评估语言模型在巴西大学入学考试中的表现 chain-of-thought
24 Measuring LLM Code Generation Stability via Structural Entropy 通过结构熵评估大型语言模型代码生成的稳定性 large language model
25 Comparing energy consumption and accuracy in text classification inference 评估文本分类推理中的能耗与准确性权衡 large language model
26 ReviewGraph: A Knowledge Graph Embedding Based Framework for Review Rating Prediction with Sentiment Features 提出ReviewGraph框架以解决酒店客户评价评分预测问题 large language model ✅
27 MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment 提出MGT-Prism以解决机器生成文本检测的领域泛化问题 large language model
28 CRISP: Persistent Concept Unlearning via Sparse Autoencoders 提出CRISP以解决大语言模型知识去除问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
29 Lexical Hints of Accuracy in LLM Reasoning Chains 提出词汇提示以提高大型语言模型推理链的准确性 reinforcement learning large language model chain-of-thought
30 ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs 提出ProMed以解决医疗LLMs反应性不足问题 reinforcement learning large language model
31 Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports 提出粗到细个性化LLM印象生成框架以解决放射科报告问题 reinforcement learning RLHF large language model
32 Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization 提出LongMab-PO以解决长上下文LLM偏好优化问题 DPO direct preference optimization large language model ✅
33 Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR 提出自我博弈与变分问题合成以提升RLVR性能 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🔗⭐
34 MMReview: A Multidisciplinary and Multimodal Benchmark for LLM-Based Peer Review Automation 提出MMReview以解决学术同行评审自动化的评估标准缺失问题 manipulation large language model multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页