cs.CL（2024-07-09）

📊 共 26 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) (22 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models 综述视觉-语言导航：聚焦基础模型时代的方法与未来机遇 VLN foundation model
2 Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps Lookback Lens：仅用注意力机制检测并缓解大语言模型中的上下文幻觉问题 large language model
3 Using Large Language Models for Generating Smart Contracts for Health Insurance from Textual Policies 利用大型语言模型从文本保单生成健康保险智能合约 large language model
4 Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models 构建语音偏见评估工具包，揭示语音集成大语言模型中的语义性别偏见 large language model
5 Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models GlobalBias数据集揭示大型语言模型中性别与族裔刻板印象，并发现模型越大刻板印象越强。 large language model
6 Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models 大型语言模型中宗教的偏见、刻板印象、污名化和情感表征研究 large language model
7 AI-AI Bias: large language models favor communications generated by large language models 揭示LLM偏好：大型语言模型更倾向于LLM生成的文本，或导致反人类歧视。 large language model
8 Learn and Don't Forget: Adding a New Language to ASR Foundation Models 针对ASR基础模型，提出多种高效方法集成新语种并保持原有性能。 foundation model
9 Using Pretrained Large Language Model with Prompt Engineering to Answer Biomedical Questions 利用预训练大语言模型与提示工程解决生物医学问答任务 large language model
10 Large Language Models can impersonate politicians and other public figures 大型语言模型可模仿政治人物，其生成内容在真实性上甚至超越真人 large language model
11 Combining Knowledge Graphs and Large Language Models 综述知识图谱与大语言模型融合方法，应对幻觉和领域知识不足问题 large language model
12 Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence 提出互联网代理框架以解决多代理协作中的集成与适应性问题 embodied AI large language model ✅
13 AnyTaskTune: Advanced Domain-Specific Solutions through Task-Fine-Tuning 提出AnyTaskTune，通过任务精调提升LLM在特定领域任务上的性能。 large language model ✅
14 Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning 揭示归纳头在上下文学习中模式匹配的关键作用 large language model
15 ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization 提出ICLGuard，通过微调控制LLM在上下文学习中的适用性授权。 large language model
16 Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis 提出SEA框架，通过标准化、评估与分析实现论文自动同行评审。 large language model
17 Measuring Sustainability Intention of ESG Fund Disclosure using Few-Shot Learning 提出一种基于Few-Shot Learning的ESG基金披露可持续性意图评估方法 large language model
18 Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders Safe-Embed：揭示句子编码器中的安全关键知识，提升大语言模型安全性 large language model ✅
19 SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training 提出SoftDedup方法，通过数据重加权加速大语言模型预训练，提升训练效率。 large language model
20 Virtual Personas for Language Models via an Anthology of Backstories Anthology：通过人物背景故事集，为语言模型构建虚拟角色。 large language model ✅
21 OffsetBias: Leveraging Debiased Data for Tuning Evaluators OffsetBias：利用去偏数据微调评估器，提升LLM评估的鲁棒性。 large language model
22 Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons 通过检测任务特定神经元，理解LLM的多任务学习泛化能力 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🔗⭐
23 FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation FBI-LLM：通过自回归蒸馏从头训练全二值化大语言模型 distillation large language model ✅
24 LIONs: An Empirically Optimized Approach to Align Language Models 提出LIONs以优化语言模型的对齐能力 preference learning DPO instruction following ✅
25 Efficient and Accurate Memorable Conversation Model using DPO based on sLLM 基于sLLM和DPO的高效准确记忆对话模型，提升多轮对话性能 DPO

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
26 Media Manipulations in the Coverage of Events of the Ukrainian Revolution of Dignity: Historical, Linguistic, and Psychological Approaches 分析乌克兰尊严革命期间媒体操纵，提出基于历史、语言和心理学的方法 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页