cs.CL（2024-09-21）

📊 共 15 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models 提出ChemEval以解决化学领域LLM评估不足问题 large language model instruction following ✅
2 Instruction Following without Instruction Tuning 揭示隐式指令调优：仅凭响应或领域数据微调即可实现指令遵循 instruction following
3 Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis 通过比较神经元分析解读大语言模型中的算术机制 large language model ✅
4 Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas 大型语言模型角色扮演悖论：推理性能提升与伦理困境 large language model
5 Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank 提出基于大语言模型的Overgenerate-and-Rank方法，自动生成关键词助记法，辅助词汇学习。 large language model
6 GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion GroupDebate：利用分组讨论提升多智能体辩论效率，降低token成本 large language model chain-of-thought
7 Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm Obliviate：中和参数高效微调中与任务无关的后门攻击 large language model ✅
8 PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL PTD-SQL：利用LLM进行文本到SQL的查询分组划分与针对性训练，提升模型推理能力。 large language model ✅
9 Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks 提出RaC框架，通过重述和对比微调语言模型，提升通信网络理解能力 large language model
10 Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers 探究预训练语言模型子层中多义词上下文定位能力 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🔗⭐
11 Contrastive Learning for Knowledge-Based Question Generation in Large Language Models 提出基于对比学习的知识型问题生成方法，提升大语言模型在知识密集型任务中的表现。 contrastive learning large language model chain-of-thought
12 Temporally Consistent Factuality Probing for Large Language Models 提出TeCFaP任务与TEMP-COFAC数据集，并设计CoTSeLF框架提升LLM的时间一致性事实性 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🔗⭐
13 Uncovering Latent Chain of Thought Vectors in Language Models 通过激活空间干预，在语言模型中诱导潜在的思维链向量 manipulation chain-of-thought
14 Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models 提出BlockWorld-Repairs数据集，评估多模态语言模型处理用户纠错能力 manipulation instruction following

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends 综述性论文：在LLM时代，系统化会话分析任务，弥合研究与商业应用间的差距。 scene reconstruction large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页