cs.CL（2024-03-05）

📊 共 41 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) (34 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (34 篇)

#题目一句话要点标签🔗⭐
1 Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering 提出Design2Code基准以解决前端工程中的多模态代码生成问题 large language model multimodal
2 Detecting Concrete Visual Tokens for Multimodal Machine Translation 提出新方法以解决多模态机器翻译中的视觉标记检测问题 multimodal visual grounding
3 Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types 提出基于大语言模型的数据增强框架以解决事件论元提取问题 large language model
4 JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models 提出两步法以解决多模态情感原因分析问题 multimodal
5 Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges 利用大型语言模型进行数据增强以解决数据稀缺问题 large language model
6 SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Models 构建SQLBench以全面评估大语言模型的Text-to-SQL能力 large language model
7 DPPA: Pruning Method for Large Language Model to Model Merging 提出DPPA以解决复杂模型合并中的参数冲突问题 large language model
8 Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models 针对越南语的LLM微调与评估框架的提出 large language model
9 Scope of Large Language Models for Mining Emerging Opinions in Online Health Discourse 提出基于LLM的框架以挖掘在线健康讨论中的新兴观点 large language model
10 CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following 提出CoGenesis框架以解决用户隐私与指令执行效率问题 instruction following
11 Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution 研究大型语言模型中的性别情感归属问题 large language model
12 Adding Multimodal Capabilities to a Text-only Translation Model 提出多模态能力增强文本翻译模型以解决过拟合问题 multimodal
13 The Case for Evaluating Multimodal Translation Models on Text Datasets 提出新的评估框架以提升多模态翻译模型的评估准确性 multimodal
14 In-Memory Learning: A Declarative Learning Framework for Large Language Models 提出一种内存学习框架以解决无标签数据环境中的自我提升问题 large language model
15 Towards Training A Chinese Large Language Model for Anesthesiology 提出Hypnos以解决中国麻醉学领域大语言模型不足问题 large language model
16 InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents 提出InjecAgent以评估工具集成LLM代理的间接提示注入攻击风险 large language model ✅
17 Exploring the Limitations of Large Language Models in Compositional Relation Reasoning 提出多语言基准以评估大语言模型的组合关系推理能力 large language model
18 Android in the Zoo: Chain-of-Action-Thought for GUI Agents 提出Chain-of-Action-Thought以提升GUI代理的任务执行能力 large language model
19 KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents 提出KnowAgent以解决LLM代理规划不足问题 large language model ✅
20 InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answers 提出一种新方法以检测大型语言模型生成答案中的幻觉现象 large language model
21 MathScale: Scaling Instruction Tuning for Mathematical Reasoning 提出MathScale以提升数学推理能力的LLM表现 large language model
22 Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding 提出多尺度位置编码以解决大语言模型中间信息丢失问题 large language model ✅
23 DIVERSE: A Dataset of YouTube Video Comment Stances with a Data Programming Model 提出DIVERSE数据集以解决军事招募舆论分析问题 large language model
24 "In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning 提出对话中学习框架以解决个性化对话生成问题 large language model
25 AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation 提出AgentsCourt框架以提升司法决策智能化 large language model
26 HARGPT: Are LLMs Zero-Shot Human Activity Recognizers? 提出HARGPT以解决零-shot人类活动识别问题 large language model
27 Guardrail Baselines for Unlearning in LLMs 提出基于护栏的方法以解决大语言模型的遗忘问题 large language model
28 MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets 提出MAGID以解决多模态对话数据不足问题 multimodal
29 PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset 提出PARADISE以评估语言模型的隐式规划能力 large language model ✅
30 Socratic Reasoning Improves Positive Text Rewriting 提出SocraticReframe以改善负面文本重写问题 large language model
31 An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 研究表明微调评估模型无法替代GPT-4的通用性 large language model
32 Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment 提出Causal Walk以解决多跳事实验证中的偏差问题 large language model ✅
33 Revisiting Meta-evaluation for Grammatical Error Correction 提出SEEDA数据集以解决英语语法错误纠正的评估偏差问题 large language model
34 Improving Event Definition Following For Zero-Shot Event Detection 提出多样化事件定义以提升零-shot事件检测性能 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
35 Learning to Maximize Mutual Information for Chain-of-Thought Distillation 提出基于互信息最大化的链式思维蒸馏方法以提升模型推理能力 distillation chain-of-thought ✅
36 Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment 提出因果提示方法以解决大型语言模型偏见问题 contrastive learning large language model chain-of-thought
37 DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation 提出DP-CRE框架以解决持续关系提取中的灾难性遗忘问题 contrastive learning structure preservation
38 Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models 提出REGA策略以解决大语言模型的灾难性遗忘问题 distillation large language model
39 Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots 提出基于教材生成教师-学生互动以开发教育聊天机器人 teacher-student large language model
40 Language Guided Exploration for RL Agents in Text Environments 提出语言引导探索框架以提升RL代理在文本环境中的决策能力 reinforcement learning decision transformer large language model
41 Learning to Use Tools via Cooperative and Interactive Agents 提出ConAgents框架以解决工具学习中的灵活性与适应性问题 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页