cs.CL（2024-02-21）

📊 共 65 篇论文 | 🔗 17 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (57 🔗16) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (57 篇)

#题目一句话要点标签🔗⭐
1 Ranking Large Language Models without Ground Truth 提出无需真实标签的语言模型排名方法 large language model
2 Large Language Models for Data Annotation and Synthesis: A Survey 利用大型语言模型自动化数据标注与合成 large language model
3 MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms 提出MM-Soc基准以评估多模态大语言模型在社交媒体中的表现 large language model multimodal ✅
4 PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain 提出PCA-Bench以评估多模态大语言模型在决策中的能力 large language model multimodal
5 RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models 提出RefuteBench以评估大型语言模型对反驳指令的响应能力 large language model instruction following
6 A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation 提出多模态上下文调优方法以解决电商产品描述生成问题 large language model multimodal ✅
7 Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment 提出认知视觉语言映射器以解决多模态理解中的知识对齐问题 large language model multimodal ✅
8 OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems 提出OlympiadBench以评估AGI在双语多模态科学问题上的能力 large language model multimodal ✅
9 Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning 提出FRODO框架以解决链式推理的可信度问题 large language model chain-of-thought
10 LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons 提出LexC-Gen以解决极低资源语言数据匮乏问题 large language model
11 What's in a Name? Auditing Large Language Models for Race and Gender Bias 审计大型语言模型以解决种族和性别偏见问题 large language model
12 Dynamic Evaluation of Large Language Models by Meta Probing Agents 提出元探测代理以解决大语言模型评估问题 large language model ✅
13 ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling 提出ARL2以解决检索器与大语言模型不匹配问题 large language model ✅
14 Understanding the Dataset Practitioners Behind Large Language Model Development 分析大型语言模型开发中的数据集从业者角色与挑战 large language model
15 Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media 提出Bangla AI框架以提升民族媒体的机器翻译能力 large language model
16 FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models 提出FanOutQA以评估大型语言模型的多跳多文档问答能力 large language model
17 Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models 提出跨语言一致性评估以解决文本水印的有效性问题 large language model ✅
18 Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content 提出诱饵与替换攻击以揭示大型语言模型的安全隐患 large language model
19 Kuaiji: the First Chinese Accounting Large Language Model 提出Kuaiji以解决会计领域大语言模型适应性不足问题 large language model
20 CriticEval: Evaluating Large Language Model as Critic 提出CriticEval以全面评估大语言模型的批评能力 large language model
21 Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models 提出神经元退化知识概念以解析大型语言模型的事实知识存储机制 large language model
22 SaGE: Evaluating Moral Consistency in Large Language Models 提出SaGE以评估大型语言模型的道德一致性问题 large language model
23 Round Trip Translation Defence against Large Language Model Jailbreaking Attacks 提出回程翻译方法以应对大型语言模型的监狱破解攻击 large language model ✅
24 Hallucinations or Attention Misdirection? The Path to Strategic Value Extraction in Business Using Large Language Models 提出PGI方法以解决大语言模型中的注意力误导问题 large language model
25 Calibrating Large Language Models with Sample Consistency 提出基于一致性度量的校准方法以提升大语言模型的置信度 large language model
26 Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models 揭示大语言模型评估中的概率误差问题 large language model
27 Factual consistency evaluation of summarization in the Era of large language models 提出TreatFact数据集以解决自动生成摘要的事实一致性评估问题 large language model
28 CMNER: A Chinese Multimodal NER Dataset based on Social Media 提出CMNER数据集以解决中文多模态命名实体识别问题 multimodal
29 GCOF: Self-iterative Text Generation for Copywriting Using Large Language Model 提出GCOF框架以提升营销文案生成效率与客户参与度 large language model
30 MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models 提出MlingConf以解决多语言信心估计不足问题 large language model
31 Knowledge Graph Enhanced Large Language Model Editing 提出GLAME以解决大语言模型知识更新问题 large language model
32 ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling 提出ThinkNote以解决大型语言模型知识整合不足的问题 large language model ✅
33 OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models 提出OMGEval以评估多语言大语言模型的生成能力 large language model ✅
34 The Lay Person's Guide to Biomedicine: Orchestrating Large Language Models 提出Explain-then-Summarise框架以改善生物医学文献的简化问题 large language model
35 CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory 提出CAMELoT以解决长输入序列处理问题 large language model
36 BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models 提出BBA方法以解决多模态推理中的表现不一致问题 multimodal chain-of-thought
37 User-LLM: Efficient LLM Contextualization with User Embeddings 提出User-LLM以高效整合用户嵌入数据 large language model
38 Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks 提出检索增强数据增强方法以解决低资源领域任务问题 large language model
39 Driving Generative Agents With Their Personality 利用个性化信息驱动生成性角色以提升游戏体验 large language model
40 Technical Report on the Pangram AI-Generated Text Classifier 提出Pangram Text以解决AI文本与人类文本识别问题 large language model
41 LLM Based Multi-Agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain 提出基于LLM的多代理生成公共管理领域半结构化文档的方法 large language model
42 Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction 提出表格提示以解决关系三元组提取中的学习挑战 large language model
43 KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection 提出基于微调LLM的多语言机器生成文本检测方法 large language model
44 Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions 提出Self-DC框架以解决组合未知问题的回答挑战 large language model
45 Potential and Challenges of Model Editing for Social Debiasing 提出模型编辑方法以解决社会偏见问题 large language model
46 $Se^2$: Sequential Example Selection for In-Context Learning 提出$Se^2$以解决示例选择在上下文学习中的不足问题 large language model ✅
47 LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens 提出LongRoPE以扩展LLM上下文窗口至2048k标记 large language model
48 Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding 提出Ouroboros以提高推测解码的效率和速度 large language model ✅
49 $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens 提出$ackslashackslash ext{∞}Bench$以解决长文本处理评估问题 large language model
50 Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent 提出Neeko框架以解决多角色扮演代理的适应性问题 large language model ✅
51 Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions? 研究多语言指令调优以提升跨语言模型性能 instruction following
52 KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge 提出KorNAT以评估韩国社会价值观与常识的对齐 large language model ✅
53 WinoViz: Probing Visual Properties of Objects Under Different States 提出WinoViz以探究对象在不同状态下的视觉属性 large language model
54 LongWanjuan: Towards Systematic Measurement for Long Text Quality 提出LongWanjuan以系统性评估长文本质量问题 foundation model ✅
55 RecMind: Japanese Movie Recommendation Dialogue with Seeker's Internal State 提出RecMind以解决日本电影推荐对话中的内在状态分析问题 chain-of-thought
56 RITFIS: Robust input testing framework for LLMs-based intelligent software 提出RITFIS框架以解决LLM智能软件的鲁棒性测试问题 large language model
57 GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis 提出GradSafe以检测大型语言模型中的越狱提示 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
58 FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models 提出FLAME以解决低资源环境下的分类法扩展问题 reinforcement learning large language model PaLM-E
59 Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation 提出蒸馏对比解码以提升大型语言模型推理能力 distillation large language model chain-of-thought
60 Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning 提出自蒸馏微调方法以解决语言模型微调中的分布差距问题 distillation large language model instruction following ✅
61 Privacy-Preserving Instructions for Aligning Large Language Models 提出合成指令以解决大语言模型隐私风险问题 reinforcement learning large language model
62 Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning 提出基于真实标签的图像描述生成方法以提升描述的独特性 reinforcement learning multimodal
63 From Text to CQL: Bridging Natural Language and Corpus Search Engine 提出文本到CQL的自动转换方法以解决查询构建复杂性问题 CQL large language model
64 An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling 提出双阶段课程学习框架以提升序列标注模型性能 curriculum learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
65 Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment 提出对LLM评估的对抗攻击研究以解决鲁棒性问题 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页