cs.CL（2024-07-16）

📊 共 28 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) (26 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection 提出IMFND框架，利用小模型概率指导，提升大型视觉语言模型在多模态假新闻检测中的性能 large language model multimodal
2 SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning SELF-GUIDE：通过自合成微调提升特定任务指令跟随能力 large language model instruction following
3 Predicting Emotion Intensity in Polish Political Texts: Comparing Supervised Models and Large Language Models in a Resource-Poor Language 比较监督模型与大语言模型，预测波兰语政治文本中的情感强度 large language model
4 InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification InstructAV：指令微调大型语言模型用于作者身份验证 large language model
5 Large Language Models as Misleading Assistants in Conversation 研究表明大型语言模型在对话中可能作为误导性助手，显著降低阅读理解任务准确率。 large language model
6 Educational Personalized Learning Path Planning with Large Language Models 利用大型语言模型进行教育个性化学习路径规划 large language model
7 MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models MINI-LLM：面向大语言模型的内存高效结构化剪枝方法 large language model
8 A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting 针对时序事件预测，构建基准数据集并全面评估大语言模型能力 large language model
9 AdaptEval: Evaluating Large Language Models on Domain Adaptation for Text Summarization 提出AdaptEval评估套件，用于评估大型语言模型在文本摘要领域迁移能力 large language model
10 How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models 提出基于大语言模型的谈判模拟框架，探究人格特质对谈判结果的影响 large language model
11 Representation Bias in Political Sample Simulations with Large Language Models 利用大型语言模型模拟政治样本时的代表性偏差研究 large language model
12 SwitchCIT: Switching for Continual Instruction Tuning SwitchCIT：通过切换机制实现持续指令调优，缓解灾难性遗忘 large language model multimodal
13 States Hidden in Hidden States: LLMs Emerge Discrete State Representations Implicitly 揭示LLM隐式离散状态表征：无需CoT涌现复杂计算能力 large language model chain-of-thought
14 Whitening Not Recommended for Classification Tasks in LLMs 大型语言模型分类任务中，不建议使用白化操作 large language model
15 NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities NeedleBench：评估LLM在不同信息密度下的检索与推理能力 large language model ✅
16 What's Wrong? Refining Meeting Summaries with LLM Feedback 提出基于多LLM反馈的会议纪要优化方法，提升纪要质量。 large language model
17 LoFTI: Localization and Factuality Transfer to Indian Locales LoFTI：针对印度地区的LLM本地化和事实性迁移评测基准 large language model
18 BinaryAlign: Word Alignment as Binary Sequence Labeling BinaryAlign：提出一种基于二元序列标注的统一词对齐方法 foundation model
19 PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation PipeInfer：利用异步流水线推测加速LLM推理 large language model
20 Vectoring Languages 提出一种基于线性代数类比的语言结构，以更好地反映语言模型的机制并捕捉语言的多样性。 large language model
21 CCoE: A Compact and Efficient LLM Framework with Multi-Expert Collaboration for Resource-Limited Settings CCoE：一种紧凑高效的LLM框架，通过多专家协作解决资源受限场景问题。 large language model
22 Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference Ada-KV：通过自适应预算分配优化KV缓存淘汰，提升LLM推理效率 large language model ✅
23 Do LLMs have Consistent Values? 通过“价值锚定”提示策略，研究LLM在心理学价值结构上与人类的一致性 large language model
24 ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models 提出ReFeR框架，利用LLM/VLM分层结构提升生成模型评估与推理能力。 large language model ✅
25 Revisiting the Impact of Pursuing Modularity for Code Generation 研究表明模块化编程未必能提升LLM代码生成性能 large language model
26 Reliable Reasoning Beyond Natural Language 提出神经符号推理方法，提升大语言模型在复杂推理任务上的可靠性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
27 InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains 提出InvAgent，利用大语言模型解决供应链库存管理中的多智能体决策问题 reinforcement learning large language model chain-of-thought
28 Robust Utility-Preserving Text Anonymization Based on Large Language Models 提出基于大语言模型的鲁棒效用保持文本匿名化框架，提升抗LLM重识别能力。 distillation large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页