cs.CL（2024-08-14）

📊 共 15 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models 提出Spoken Stereoset数据集，用于评估语音大语言模型中针对说话者的社会偏见。 large language model multimodal
2 ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model ONSEP：一种基于大语言模型的在线神经符号事件预测新框架 large language model
3 Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models 揭示大语言模型终身知识编辑失败的原因：知识叠加现象 large language model ✅
4 Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics 揭示GPT语言模型人格分裂问题：基于无基质心理测量学的研究 large language model foundation model
5 Fast Training Dataset Attribution via In-Context Learning 提出基于上下文学习的快速训练数据归因方法，提升LLM数据贡献评估效率。 large language model
6 Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions 提出对齐增强解码(AED)，通过token级自适应优化概率分布防御大语言模型越狱攻击。 large language model ✅
7 A Quantum-Inspired Analysis of Human Disambiguation Processes 利用量子力学形式化方法分析并重现人类歧义消解过程，性能优于现有NLP方法。 large language model
8 The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models 利用大型语言模型，本文提出一种无需模式链接的Text-to-SQL方法，并在BIRD基准上取得领先。 large language model
9 WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs WeKnow-RAG：融合Web搜索与知识图谱的自适应检索增强生成方法 large language model
10 From Brazilian Portuguese to European Portuguese 提出一种基于LLM微调的巴西葡萄牙语到欧洲葡萄牙语翻译系统，并构建了高质量测试集。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization 提出BMC框架，通过桥接和建模成对数据相关性，提升DPO的对齐性能 DPO direct preference optimization large language model ✅
12 Large Language Models Prompting With Episodic Memory 提出基于情景记忆的大语言模型提示优化方法POEM，提升小样本学习性能。 reinforcement learning large language model
13 Large Language Models Know What Makes Exemplary Contexts 提出基于强化学习的上下文学习框架，提升大语言模型的Few-shot性能 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
14 Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques 探索高级Prompting技术在对话式精神操控检测中的有效性 manipulation chain-of-thought
15 Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations 通过可控操纵评估词汇语义在跨语言迁移中的作用 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页