cs.CL（2024-05-21）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Investigating Symbolic Capabilities of Large Language Models 评估大语言模型在符号计算任务中的能力，揭示其在复杂性增加时的性能下降 large language model chain-of-thought
2 Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models 提出AoR框架，通过分层推理聚合提升大语言模型在复杂推理任务中的答案选择能力 large language model chain-of-thought
3 Topic Classification of Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgment 利用大型语言模型和英国法律新分类法进行案例法主题分类，洞察即决判决 large language model
4 Investigating Persuasion Techniques in Arabic: An Empirical Study Leveraging Large Language Models 利用大型语言模型研究阿拉伯语中的说服技巧 large language model
5 Large Language Models Meet NLP: A Survey 综述性研究：探索大型语言模型在自然语言处理中的应用与未来 large language model
6 RecGPT: Generative Pre-training for Text-based Recommendation 提出RecGPT-7B，首个面向文本推荐领域微调的大语言模型，显著提升推荐性能。 large language model instruction following ✅
7 Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum 提出数据集分解方法，通过变长序列训练加速LLM训练。 large language model
8 Tagengo: A Multilingual Chat Dataset Tagengo：构建高质量多语聊天数据集，提升开源LLM多语能力 large language model
9 Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models 提出基于稀疏自编码器的电路识别方法，提升语言模型可解释性 large language model
10 Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction 提出基于检索增强的语言模型以解决极端多标签知识图谱链接预测问题 large language model ✅
11 Quantifying Semantic Emergence in Language Models 提出信息涌现度量（IE）以量化语言模型从token中提取语义信息的能力。 large language model
12 The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG) FutureDial-RAG挑战赛：探索检索增强生成在对话系统中的应用 large language model
13 Equipping Transformer with Random-Access Reading for Long-Context Understanding 提出随机访问Transformer，解决长文本理解中序列依赖和效率瓶颈问题 large language model
14 Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression 提出DecoQuant，一种基于矩阵分解的无数据低比特量化方法，用于压缩KV缓存。 large language model
15 SirLLM: Streaming Infinite Retentive LLM SirLLM：流式无限记忆LLM，无需微调实现长程对话记忆 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
16 Comparative Analysis of Different Efficient Fine Tuning Methods of Large Language Models (LLMs) in Low-Resource Setting 在低资源环境下，对比分析大语言模型高效微调方法，探索Context Distillation的潜力。 distillation large language model
17 Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents 提出对抗性DPO（ADPO）算法，利用有害数据降低对话系统毒性，同时保持连贯性和非规避性。 DPO direct preference optimization large language model
18 LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language 提出LLM Processes，利用自然语言引导LLM进行数值预测分布建模。 predictive model large language model
19 Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction 提出基于自指令微调的事实核查方法，兼顾准确性、可解释性和泛化性。 DPO contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页