cs.CL（2024-02-15）

📊 共 31 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (25 🔗5) 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) (25 篇)

#题目一句话要点标签🔗⭐
1 EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models 提出高效细粒度去学习框架以解决多模态大语言模型的幻觉问题 large language model multimodal
2 BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains 提出BioMistral以解决医学领域LLM适应性不足问题 large language model foundation model
3 Chain-of-Thought Reasoning Without Prompting 提出无提示链式推理方法以提升大语言模型推理能力 large language model chain-of-thought
4 Answer is All You Need: Instruction-following Text Embedding via Answering the Question 提出InBedder以解决用户导向文本嵌入问题 large language model instruction following
5 Uncertainty Quantification for In-Context Learning of Large Language Models 提出不确定性量化方法以解决大语言模型的响应信任问题 large language model ✅
6 PAL: Proxy-Guided Black-Box Attack on Large Language Models 提出PAL以解决大语言模型的黑箱攻击问题 large language model ✅
7 Enhancing Large Language Models with Pseudo- and Multisource- Knowledge Graphs for Open-ended Question Answering 提出PG&AKV框架以解决大语言模型的幻觉问题 large language model
8 Efficient Language Adaptive Pre-training: Extending State-of-the-Art Large Language Models for Polish 提出语言自适应预训练方法以提升波兰语生成能力 large language model
9 Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence 提出MoEI方法以提升大型语言模型的情感智能 large language model
10 Towards Safer Large Language Models through Machine Unlearning 提出选择性知识否定遗忘框架以解决大语言模型的有害知识问题 large language model
11 AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator 提出AI Hospital框架以解决医疗互动中LLMs应用不足问题 large language model ✅
12 Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection 提出上下文感知注意力框架以解决多模态仇恨内容检测问题 multimodal ✅
13 LAPDoc: Layout-Aware Prompting for Documents 提出LAPDoc以提升文本基础LLM在文档理解中的表现 large language model
14 OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset 提出OpenMathInstruct-1以解决数学指令调优数据集不足问题 large language model
15 Self-Augmented In-Context Learning for Unsupervised Word Translation 提出自增强上下文学习以解决无监督词翻译问题 large language model
16 Multi-word Tokenization for Sequence Compression 提出多词元标记化方法以解决序列压缩问题 large language model
17 Generative Representational Instruction Tuning 提出生成表征指令调优方法以解决文本生成与嵌入任务的统一问题 large language model ✅
18 SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs 提出SportsMetrics以评估LLMs在体育数据分析中的信息融合能力 large language model
19 A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts 提出ReadAgent以解决长文本理解能力不足的问题 large language model
20 TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation 提出TDAG框架以解决复杂任务执行中的适应性问题 large language model
21 Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence 提出PDD以解决长文本生成中的话语连贯性评估问题 large language model
22 Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients 提出知识注入的对话健康助手以改善糖尿病患者管理 large language model
23 TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles 提出TOAD以解决任务导向对话数据生成的挑战 large language model
24 Case Study: Testing Model Capabilities in Some Reasoning Tasks 探讨大型语言模型在推理任务中的能力与局限性 large language model
25 Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States 提出实验框架以探究LLM对幻觉的认知 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🔗⭐
26 RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models 提出RS-DPO以解决大语言模型对齐中的不稳定性问题 reinforcement learning PPO RLHF
27 UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models 提出UnDIAL以解决大语言模型中的敏感信息去除问题 distillation large language model
28 Model Compression and Efficient Inference for Large Language Models: A Survey 提出大语言模型压缩与高效推理方法以解决资源受限设备的挑战 distillation large language model
29 NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models 提出NutePrune以解决大语言模型的高效剪枝问题 distillation large language model ✅
30 Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning 提出选择性反射调优以提升LLM指令调优数据质量 teacher-student large language model instruction following

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
31 A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents 提出系统性框架以映射语言代理的对抗攻击 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页