cs.CL（2024-02-22）

📊 共 55 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (51 🔗8) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (51 篇)

#题目一句话要点标签🔗⭐
1 Towards Robust Instruction Tuning on Multimodal Large Language Models 提出INSTRAUG以增强多模态大语言模型的指令调优能力 large language model multimodal instruction following
2 PALO: A Polyglot Large Multimodal Model for 5B People 提出PALO以解决多语言视觉-语言模型的包容性问题 large language model multimodal ✅
3 Chain-of-Thought Unfaithfulness as Disguised Accuracy 提出链式思维不可信度作为隐性准确性评估方法 large language model chain-of-thought
4 Zero-shot cross-lingual transfer in instruction tuning of large language models 研究零样本跨语言迁移以优化大语言模型的指令调优 large language model instruction following
5 ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models 提出ConceptMath以评估大型语言模型的数学推理能力 large language model foundation model
6 Can Large Language Models Detect Misinformation in Scientific News Reporting? 提出利用大型语言模型检测科学新闻中的虚假信息 large language model chain-of-thought
7 Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective 提出新方法以缓解多模态幻觉问题 multimodal
8 Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models 提出专家剪枝与跳过方法以提升MoE大语言模型的部署效率 large language model ✅
9 Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond 提出统一任务嵌入框架以解决多模型适应性问题 large language model
10 Identifying Multiple Personalities in Large Language Models with External Evaluation 提出外部评估方法以识别大语言模型的多重人格 large language model
11 MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues 提出MT-Bench-101以解决多轮对话评估不足问题 large language model ✅
12 Efficient and Effective Vocabulary Expansion Towards Multilingual Large Language Models 提出EEVE方法以提升多语言大模型的韩语处理能力 large language model
13 On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe 通过反向字典探测提升大语言模型的概念推理能力 large language model
14 Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models 提出STORM系统以解决从零开始撰写维基百科式文章的问题 large language model
15 RelayAttention for Efficient Large Language Model Serving with Long System Prompts 提出RelayAttention以解决长系统提示下的LLM服务效率问题 large language model
16 Unveiling Linguistic Regions in Large Language Models 揭示大型语言模型中的语言区域以提升跨语言能力 large language model
17 UFO: a Unified and Flexible Framework for Evaluating Factuality of Large Language Models 提出UFO框架以解决大型语言模型事实性评估问题 large language model ✅
18 Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality 探讨大型语言模型个性的一致性与行动的关系 large language model
19 LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition 提出LLM-DA以解决少样本命名实体识别数据增强问题 large language model
20 Small Language Models as Effective Guides for Large Language Models in Chinese Relation Extraction 提出SLCoLM框架以解决长尾数据问题 large language model
21 Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models? 提出故事作为更优的常识表达方式以提升大语言模型的推理能力 large language model
22 INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models 提出INSTRUCTIR基准以解决信息检索模型指令跟随能力不足的问题 instruction following
23 Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration 提出FACTUAL以解决大型语言模型在立场检测中的偏见问题 large language model
24 Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education 提出CGLLM以解决NLP教育中的概念图恢复与问答问题 large language model
25 Towards Understanding Counseling Conversations: Domain Knowledge and Large Language Models 提出结合领域知识与大语言模型以提升咨询对话理解 large language model
26 GenCeption: Evaluate Vision LLMs with Unlabeled Unimodal Data 提出GenCeption以解决多模态大语言模型评估的高成本问题 large language model multimodal
27 Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs 研究数字标记化对前沿LLM算术性能的影响 large language model chain-of-thought
28 Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments 提出中间件工具以增强LLM在复杂环境中的能力 generalist agent large language model
29 LLMBind: A Unified Modality-Task Integration Framework 提出LLMBind框架以解决多模态任务集成问题 large language model multimodal
30 Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge 提出Hint-before-Solving Prompting以提升LLMs的推理能力 large language model chain-of-thought ✅
31 Qsnail: A Questionnaire Dataset for Sequential Question Generation 提出Qsnail数据集以解决问卷生成的挑战 large language model chain-of-thought ✅
32 Divide-or-Conquer? Which Part Should You Distill Your LLM? 提出任务分解策略以提升大语言模型的推理能力 large language model
33 tinyBenchmarks: evaluating LLMs with fewer examples 提出tinyBenchmarks以降低LLM评估成本 large language model
34 Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking 研究细调如何增强语言模型的实体追踪能力 instruction following
35 CriticBench: Benchmarking LLMs for Critique-Correct Reasoning 提出CriticBench以评估大型语言模型的批判与纠正推理能力 large language model
36 IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus 提出IEPile以解决信息提取领域数据不足问题 large language model
37 LLM-Assisted Content Conditional Debiasing for Fair Text Embedding 提出内容条件去偏见方法以实现公平文本嵌入 large language model
38 MultiLS: A Multi-task Lexical Simplification Framework 提出MultiLS框架以解决多任务词汇简化问题 large language model
39 Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning 提出Mirror方法以解决知识丰富推理中的自我反思问题 large language model
40 Balanced Data Sampling for Language Model Training with Clustering 提出ClusterClip采样以解决语言模型训练数据不平衡问题 large language model
41 COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models 提出COBIAS框架以评估语言模型偏见基准的上下文可靠性 large language model
42 KoCoSa: Korean Context-aware Sarcasm Detection Dataset 提出KoCoSa数据集以解决韩语对话中的讽刺检测问题 large language model ✅
43 Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment 提出后门增强安全对齐方法以应对细调基础的越狱攻击 large language model
44 Dependency Annotation of Ottoman Turkish with Multilingual BERT 提出基于多语言BERT的奥斯曼土耳其依赖注释方法 large language model
45 Whose LLM is it Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard 通过语言比较实现LLM文本归属，准确率达88% large language model
46 Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance 研究提示礼貌性对大型语言模型表现的影响 large language model
47 "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models 揭示语言模型首个令牌概率与文本答案不匹配的问题 large language model
48 Rethinking Scientific Summarization Evaluation: Grounding Explainable Metrics on Facet-aware Benchmark 提出Facet-aware Metric以解决科学摘要评估不足问题 large language model
49 Assessing generalization capability of text ranking models in Polish 提出针对波兰语的重排序模型以解决泛化能力不足问题 large language model
50 Can Language Models Act as Knowledge Bases at Scale? 研究大型语言模型作为知识库的有效性与局限性 large language model
51 Eagle: Ethical Dataset Given from Real Interactions 提出Eagle数据集以解决LLM伦理问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
52 Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models 提出学习减少框架以优化结构化数据在大语言模型中的表示 reinforcement learning large language model
53 Unintended Impacts of LLM Alignment on Global Representation 探讨大语言模型对全球表现的意外影响 reinforcement learning RLHF DPO
54 An LLM-Enhanced Adversarial Editing System for Lexical Simplification 提出一种无平行语料的词汇简化方法以解决低资源场景问题 distillation large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
55 A Language Model's Guide Through Latent Space 扩展概念引导框架以提升语言模型的多样性与质量 HuMoR

⬅️ 返回 cs.CL 首页 · 🏠 返回主页