cs.CL（2024-11-13）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Towards Evaluating Large Language Models for Graph Query Generation 评估大语言模型在图数据库查询生成中的能力，并发现Claude Sonnet 3.5表现最佳。 large language model chain-of-thought
2 Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models 提出动态子集调优方法，扩展大语言模型参数高效训练的操作范围 large language model
3 Knowledge Bases in Support of Large Language Models for Processing Web News 提出一种基于知识库增强的大语言模型新闻处理框架，提升新闻分类效果。 large language model
4 A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models 对比离散语音Token与连续语音特征在语义相关任务中对大语言模型的影响 large language model
5 Neural Topic Modeling with Large Language Models in the Loop 提出LLM-ITL框架，融合大语言模型与神经主题模型以提升主题可解释性。 large language model ✅
6 A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look 利用大语言模型进行相关性评估的大规模研究，探索LLM在信息检索中的应用。 large language model
7 CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs CorrSynth：一种基于相关采样的LLM多样化数据集生成方法 large language model
8 One STEP at a time: Language Agents are Stepwise Planners STEP框架：通过经验学习提升语言Agent在动态环境中的规划能力 large language model
9 Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle 提出Daily Oracle，利用每日新闻持续评估LLM的时间泛化能力与预测未来事件的能力。 large language model
10 CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt 提出CoCoP方法，利用代码补全提示增强LLM在文本分类任务中的性能 large language model
11 Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers 激活修补揭示Transformer中语言无关的概念表征 large language model
12 Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness 研究揭示LLM冒犯性判断中的人口统计偏差受混淆因素影响，需多数据集分析 large language model
13 Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding 提出Tree-of-Table方法，增强LLM在复杂大规模表格理解中的推理能力 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🔗⭐
14 CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback 提出CHAI框架，利用AI反馈强化学习提升LLM在混合代码翻译中的性能 reinforcement learning large language model
15 RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution RED：通过奖励重分配释放token级别奖励，提升LLM对齐效果 reinforcement learning RLHF large language model
16 CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision CLaSP：利用自然语言监督学习时间序列信号的概念 contrastive learning large language model
17 Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models 提出DRPO：一种无需微调的语言模型自对齐动态奖励与提示优化方法 RLHF large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页