cs.CL（2024-11-20）

📊 共 19 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) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 Patience Is The Key to Large Language Model Reasoning 提出耐心推理方法，提升大语言模型在复杂问题上的表现 large language model chain-of-thought
2 Utilizing Large Language Models to Synthesize Product Desirability Datasets 利用大语言模型合成产品吸引力数据集，降低用户情感分析成本 large language model
3 A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection 提出一种灵活的大语言模型安全防护方法，用于检测离题提示。 large language model
4 Advancing Complex Medical Communication in Arabic with Sporo AraSum: Surpassing Existing Large Language Models Sporo AraSum：超越现有大型语言模型，提升阿拉伯语复杂医疗沟通能力 large language model
5 Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine 提出MedGuard基准，评估大型语言模型在医疗领域的安全性和可信度 large language model
6 Disentangling Memory and Reasoning Ability in Large Language Models 提出解耦记忆与推理的新型LLM推理范式，提升模型可靠性与可解释性。 large language model ✅
7 AIDBench: A benchmark for evaluating the authorship identification capability of large language models AIDBench：评估大语言模型作者身份识别能力的基准 large language model
8 Mediating Modes of Thought: LLM's for design scripting 利用LLM弥合设计意图与算法逻辑，实现更易用的设计脚本生成 large language model multimodal
9 Unification of Balti and trans-border sister dialects in the essence of LLMs and AI Technology 利用LLM和AI技术统一巴尔蒂语及其跨界方言 large language model
10 Assessing Gender Bias in LLMs: Comparing LLM Outputs with Human Perceptions and Official Statistics 通过对比LLM输出与人类认知和统计数据，评估大型语言模型中的性别偏见 large language model
11 Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding 综述性研究：深入探讨提升大语言模型推理效率的推测解码方法 large language model
12 Training Bilingual LMs with Data Constraints in the Targeted Language 利用数据约束下的辅助语言提升目标语言大模型性能 large language model
13 PatentEdits: Framing Patent Novelty as Textual Entailment 提出PatentEdits数据集，将专利新颖性判定转化为文本蕴含任务，并用LLM预测专利修改。 large language model
14 A Survey on Human-Centric LLMs 综述：以人为本的大语言模型能力、应用与挑战 large language model
15 Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach 提出LLM-Modulo框架，通过LLM与验证器结合，提升LLM在规划调度任务中的鲁棒性。 large language model
16 When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training 提出AnchorAttention，解决BFloat16下RoPE长文本训练的数值问题。 large language model ✅
17 Combining Autoregressive and Autoencoder Language Models for Text Classification CAALM-TC：融合自回归与自编码语言模型提升文本分类性能 large language model
18 Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL LPE-SQL：利用可扩展的辅助知识库，提升文本到SQL的持续学习能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
19 MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers MemoryFormer：通过移除全连接层最小化Transformer计算量 linear attention large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页