cs.CL（2024-03-18）

📊 共 28 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) (26 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models 综述自动图表理解在大型基础模型中的应用与挑战 large language model foundation model ✅
2 A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models 提出工具箱以揭示大型语言模型中的健康公平偏见 large language model
3 Leveraging Large Language Models to Extract Information on Substance Use Disorder Severity from Clinical Notes: A Zero-shot Learning Approach 利用大型语言模型提取临床笔记中的物质使用障碍严重性信息 large language model
4 TnT-LLM: Text Mining at Scale with Large Language Models 提出TnT-LLM以解决大规模文本挖掘中的标签生成问题 large language model
5 EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models 提出EasyJailbreak框架以简化大语言模型的越狱攻击评估 large language model
6 Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus 提出基于LoTH的ARC基准评估LLMs推理能力 large language model
7 Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models 提出基于零-shot提示的GPT-3.5模型以提取超关系知识图谱 large language model
8 HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models 提出HateCOT以解决攻击性言论检测的泛化问题 large language model
9 Towards Enabling FAIR Dataspaces Using Large Language Models 利用大型语言模型推动FAIR数据空间的实现 large language model
10 GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture 提出GPT-4作为评估工具以提升农业害虫管理建议的质量 large language model
11 Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models 提出Counting-Stars基准以评估长上下文大语言模型的多证据检索能力 large language model
12 Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model 提出神经元级微调方法以提升大语言模型的训练效率 large language model
13 InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions 提出InsCL以解决大语言模型的持续学习问题 large language model
14 A Novel Paradigm Boosting Translation Capabilities of Large Language Models 提出新范式以提升大语言模型的翻译能力 large language model
15 X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment 提出双语大规模视觉语言对齐优化方法以解决多模态数据构建问题 large language model multimodal
16 Reference-based Metrics Disprove Themselves in Question Generation 提出无参考度量以解决问答生成评估问题 large language model
17 Using Generative Text Models to Create Qualitative Codebooks for Student Evaluations of Teaching 利用生成文本模型创建学生教学评估的定性编码书 large language model
18 QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction 提出QueryAgent以解决LLM语义解析中的可靠性与效率问题 large language model
19 Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models 提出Guide-Align以解决大型语言模型的安全与质量问题 large language model
20 Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression 评估压缩大语言模型的信任度以提升效率与安全性 large language model
21 OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety 提出OpenEval以解决中文LLM评估中的能力、对齐和安全问题 large language model
22 Zero-Shot Multi-task Hallucination Detection 提出零样本多任务幻觉检测框架以解决文本生成质量问题 large language model
23 Metaphor Understanding Challenge Dataset for LLMs 提出隐喻理解挑战数据集以评估大型语言模型的能力 large language model ✅
24 Revisiting The Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems 提出一种模型以识别和纠正韵文中的性别刻板印象 large language model
25 DEE: Dual-stage Explainable Evaluation Method for Text Generation 提出DEE以解决文本生成评估缺乏解释性的问题 large language model
26 StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation 提出StyleChat以解决LLMs在风格化对话生成中的数据不足问题 large language model

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

#题目一句话要点标签🔗⭐
27 Reinforcement Learning with Token-level Feedback for Controllable Text Generation 提出TOLE算法以解决可控文本生成中的反馈不足问题 reinforcement learning large language model ✅
28 EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents 提出EnvGen框架以生成和适应环境训练智能体 reinforcement learning curriculum learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页