cs.CL（2024-05-03）

📊 共 20 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Mothman at SemEval-2024 Task 9: An Iterative System for Chain-of-Thought Prompt Optimization	提出一种迭代式的思维链提示优化系统，提升大语言模型在横向思维任务上的表现。	large language model chain-of-thought
2	Exploring Combinatorial Problem Solving with Large Language Models: A Case Study on the Travelling Salesman Problem Using GPT-3.5 Turbo	探索大型语言模型在组合优化问题中的应用：以GPT-3.5 Turbo求解旅行商问题为例	large language model chain-of-thought
3	Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models	Vibe-Eval：用于评估多模态语言模型的新型高难度评测基准	multimodal	✅
4	PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning	提出PICLe框架，通过Persona In-Context Learning引导LLM展现特定人格行为	large language model	✅
5	Semantic Scaling: Bayesian Ideal Point Estimates with Large Language Models	提出Semantic Scaling，利用大语言模型进行文本理想点估计，提升意识形态测量灵活性。	large language model
6	Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling	提出FLAN-FinXC，通过指令调优LLM和LoRA解决金融文档中极端财务数字标签问题。	large language model
7	Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection	提出基于不确定性的双层选择方法，优化大语言模型调用成本与性能。	large language model
8	Argumentative Large Language Models for Explainable and Contestable Claim Verification	提出论证型大语言模型(ArgLLMs)，用于可解释和可辩驳的声明验证。	large language model
9	Large Multimodal Model based Standardisation of Pathology Reports with Confidence and their Prognostic Significance	提出基于大模型的多模态病理报告标准化框架，并评估其预后意义	multimodal
10	Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT	利用GPT4生成叙事文本，分析BERT在不同风格和内容下的表征差异	large language model
11	Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models	提出依赖感知半结构化稀疏(DaSS)方法，用于压缩GLU变体LLM。	large language model
12	Attribution in Scientific Literature: New Benchmark and Methods	提出REASONS数据集，解决科学文献中LLM自动引用时的幻觉问题。	large language model
13	Assessing and Verifying Task Utility in LLM-Powered Applications	AgentEval：用于评估和验证LLM应用任务效用的新框架	large language model
14	What does the Knowledge Neuron Thesis Have to do with Knowledge?	质疑知识神经元假说：大型语言模型知识存储并非仅依赖MLP权重	large language model
15	Conformal Prediction for Natural Language Processing: A Survey	综述：针对自然语言处理任务的共形预测技术及其应用	large language model
16	DALLMi: Domain Adaption for LLM-based Multi-label Classifier	DALLMi：针对LLM多标签分类器的领域自适应方法，解决目标域标签不全和训练开销大的问题。	large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
17	EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer	提出EEG2TEXT，利用脑电预训练和多视角Transformer提升开放词汇脑电信号到文本的解码精度。	open-vocabulary open vocabulary
18	A quantitative and typological study of Early Slavic participle clauses and their competition	定量分析早期斯拉夫语从句，研究分词结构及其与限定从句的竞争关系。	semantic map

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

#	题目	一句话要点	标签	🔗	⭐
19	Aloe: A Family of Fine-tuned Open Healthcare LLMs	提出Aloe医疗LLM家族，通过指令调优、模型融合和对齐，在医疗领域实现高性能和伦理标准。	direct preference optimization large language model chain-of-thought
20	SoftMCL: Soft Momentum Contrastive Learning for Fine-grained Sentiment-aware Pre-training	提出SoftMCL，通过软标签动量对比学习提升情感感知预训练效果	contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页