cs.CL（2024-02-14）

📊 共 21 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Recurrent Alignment with Hard Attention for Hierarchical Text Rating 提出RAHA框架以解决层次文本评分问题 large language model ✅
2 STEER: Assessing the Economic Rationality of Large Language Models 提出STEER方法评估大型语言模型的经济理性 large language model chain-of-thought
3 Generalization in Healthcare AI: Evaluation of a Clinical Large Language Model 评估临床大语言模型以提升医疗AI的泛化能力 large language model
4 Reasoning over Uncertain Text by Generative Large Language Models 提出BLInD数据集以解决LLM在不确定文本推理中的挑战 large language model
5 Personalized Large Language Models 提出个性化大语言模型以解决主观任务响应不足问题 large language model
6 (Ir)rationality and Cognitive Biases in Large Language Models 评估大型语言模型的非理性与认知偏差 large language model
7 DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning 提出DolphCoder以提升代码生成能力 large language model
8 Copyright Traps for Large Language Models 提出版权陷阱以检测大型语言模型中的版权内容 large language model
9 AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails 提出MWPTutor以解决LLM在教育中的教学策略不足问题 large language model
10 Multi-Query Focused Disaster Summarization via Instruction-Based Prompting 提出基于指令提示的多查询灾害摘要方法以提升信息提取能力 large language model instruction following
11 API Pack: A Massive Multi-Programming Language Dataset for API Call Generation 提出API Pack数据集以提升API调用生成能力 large language model ✅
12 AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability 提出AQA-Bench以评估大语言模型的顺序推理能力 large language model ✅
13 Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey 综述LLM对话安全的攻击、防御与评估方法 large language model ✅
14 SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks 提出SLEB以解决大语言模型冗余问题 large language model ✅
15 SyntaxShap: Syntax-aware Explainability Method for Text Generation 提出SyntaxShap以解决文本生成中的可解释性问题 large language model
16 Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications 提出AgentEval框架以评估LLM应用的任务效用 large language model
17 Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking 提出多文化知识获取方法以解决文化偏见问题 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🔗⭐
18 Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies 通过知识蒸馏与优化训练策略提升NLP任务性能 distillation large language model
19 ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization 提出ICDPO以有效借用他人对齐能力解决LLM生成安全内容问题 DPO direct preference optimization large language model
20 MaxMin-RLHF: Alignment with Diverse Human Preferences 提出MaxMin-RLHF以解决人类偏好多样性对齐问题 reinforcement learning policy learning RLHF
21 Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation 提出自对齐方法以解决大型语言模型的事实准确性问题 direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页