cs.CL（2024-02-28）

📊 共 39 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (32 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (32 篇)

#题目一句话要点标签🔗⭐
1 SparseLLM: Towards Global Pruning for Pre-trained Language Models 提出SparseLLM以解决大语言模型的全局剪枝问题 large language model
2 How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning 提出机制性理解以揭示链式思维推理的内部机制 large language model chain-of-thought
3 Collaborative decoding of critical tokens for boosting factuality of large language models 提出协作解码框架以提升大语言模型的事实性 large language model instruction following
4 Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding 提出WebLM以解决网页理解中的多模态信息整合问题 multimodal ✅
5 CLLMs: Consistency Large Language Models 提出一致性大语言模型以提升并行解码效率 large language model
6 Large Language Models and Games: A Survey and Roadmap 综述大型语言模型在游戏中的应用与未来发展 large language model
7 The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA 利用大型语言模型解决对话式多文档问答问题 large language model ✅
8 Towards Generalist Prompting for Large Language Models by Mental Models 提出通用提示方法MeMo以提升大型语言模型的任务表现 large language model
9 Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation 提出信息精炼训练方法以提升检索增强生成模型性能 large language model
10 Cause and Effect: Can Large Language Models Truly Understand Causality? 提出CARE CA框架以增强大语言模型的因果推理能力 large language model
11 Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models 提出MedLaSA以解决医疗领域知识编辑问题 large language model
12 Datasets for Large Language Models: A Comprehensive Survey 综述大型语言模型数据集以推动研究进展 large language model ✅
13 Meta-Task Prompting Elicits Embeddings from Large Language Models 提出MetaEOL方法以生成高质量文本嵌入 large language model
14 Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models 提出分解提示方法以解决多语言结构知识探测问题 large language model
15 VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models 提出VerifiNER以解决生物医学命名实体识别中的错误问题 large language model
16 Prospect Personalized Recommendation on Large Language Model-based Agent Platform 提出Rec4Agentverse以提升LLM平台的个性化推荐系统 large language model
17 Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? 探讨多语言环境下人类价值观在大型语言模型中的一致性与可控性 large language model
18 Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions 构建新数据集以提升大语言模型在医学问答中的表现 large language model ✅
19 Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension 通过局部内在维度评估大型语言模型生成文本的真实性 large language model
20 Corpus-Steered Query Expansion with Large Language Models 提出基于语料的查询扩展方法以提升信息检索效果 large language model
21 Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning 提出RIDERS以解决Commonsense推理中的Toxic CoT问题 large language model chain-of-thought
22 Learning to Compress Prompt in Natural Language Formats 提出Nano-Capsulator以解决长提示压缩与迁移性问题 large language model
23 Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication 提出非自然语言格式以提升LLM推理与沟通效率 large language model ✅
24 A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems 综述基于大语言模型的多轮对话系统的最新进展 large language model
25 A Sentiment Consolidation Framework for Meta-Review Generation 提出情感整合框架以提升科学领域的元评价生成 large language model
26 FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability 提出FoFo基准以评估大语言模型的格式遵循能力 large language model ✅
27 Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification 提出公平性框架以提升LLM分类任务的公平性 large language model
28 Learning or Self-aligning? Rethinking Instruction Fine-tuning 提出知识干预框架以解构指令微调的潜在因素 large language model
29 LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History 研究任务切换对对话历史中LLM性能的影响 large language model
30 MEGAnno+: A Human-LLM Collaborative Annotation System 提出MEGAnno+以解决人类与LLM协作标注问题 large language model
31 Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore 提出FActScore评估多语言LLM生成文本的事实准确性 large language model
32 Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions 提出LINGOLLM以解决濒危语言处理问题 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🔗⭐
33 MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery 提出MIKO框架以解决社交媒体意图理解问题 distillation large language model multimodal
34 CogBench: a large language model walks into a psychology lab 提出CogBench以全面评估大型语言模型的行为 reinforcement learning RLHF large language model
35 Small But Funny: A Feedback-Driven Approach to Humor Distillation 提出反馈驱动方法以提升幽默生成的蒸馏效果 distillation HuMoR large language model
36 3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding 提出3MVRD模型以解决复杂表单文档理解问题 distillation multimodal
37 Evaluating Quantized Large Language Models 评估量化大语言模型以降低计算成本 Mamba large language model ✅
38 Simple linear attention language models balance the recall-throughput tradeoff 提出BASED架构以平衡语言模型的召回与吞吐量 Mamba linear attention ✅
39 Towards Better Understanding of Contrastive Sentence Representation Learning: A Unified Paradigm for Gradient 提出统一范式以提升对比句子表示学习的理解与效果 representation learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页