cs.CL（2024-03-08）

📊 共 23 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) (20 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessment 提出基于错误的人工评估框架以解决LLM简化能力评估问题 large language model
2 ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models 提出ERBench以解决大语言模型评估难题 large language model multimodal
3 Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context 提出Gemini 1.5以解决多模态理解与长文档检索问题 large language model multimodal
4 Towards Multimodal Sentiment Analysis Debiasing via Bias Purification 提出多模态情感分析去偏见方法以解决数据集偏见问题 multimodal
5 A dataset and benchmark for hospital course summarization with adapted large language models 提出MIMIC-IV-BHC数据集以提升医院病程摘要生成 large language model
6 Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations 提出Alignment Studio以解决特定上下文下语言模型对齐问题 large language model
7 Are Human Conversations Special? A Large Language Model Perspective 分析大语言模型在理解人类对话中的特殊性 large language model
8 A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health 提出一种新颖的对话评估框架以改善心理健康领域的LLM应用 large language model
9 Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought 提出偏见增强一致性训练以减少链式思维中的偏见推理问题 chain-of-thought
10 Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering 提出LLMQA框架以解决开放域问答中的证据收集问题 large language model
11 Towards a Psychology of Machines: Large Language Models Predict Human Memory 利用大型语言模型预测人类记忆表现 large language model
12 LLM4Decompile: Decompiling Binary Code with Large Language Models 提出LLM4Decompile以解决二进制代码反编译问题 large language model ✅
13 Can we obtain significant success in RST discourse parsing by using Large Language Models? 利用大型语言模型提升RST话语解析的性能 large language model
14 RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation 提出检索增强思维以提升长时生成任务中的推理能力 large language model chain-of-thought ✅
15 Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs 提出评估框架以解决LLM社交互动中的信息不对称问题 large language model
16 PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design 提出PipeRAG以解决检索增强生成中的延迟问题 large language model
17 Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs 提出低资源语言任务的成本优化方法以提升处理效率 large language model
18 Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings 提出基于归因分数的分析方法以提升低资源环境下模型解释性 large language model
19 ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications 提出ACLSum数据集以解决科学出版物的多方面摘要问题 large language model ✅
20 Generator-Guided Crowd Reaction Assessment 提出CReAM任务以评估社交媒体帖子反应 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🔗⭐
21 ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models 提出ChatUIE以解决基于聊天的统一信息提取问题 reinforcement learning large language model
22 DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation 提出DiffChat以实现与文本到图像合成模型的交互式图像创作 reinforcement learning large language model instruction following
23 Will GPT-4 Run DOOM? 利用GPT-4在DOOM游戏中实现智能决策与规划 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页