cs.CL（2024-10-05）

📊 共 19 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) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#题目一句话要点标签🔗⭐
1 CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints CS4：通过控制故事写作约束数量自动评估大型语言模型的创造力 large language model instruction following ✅
2 LoRTA: Low Rank Tensor Adaptation of Large Language Models LoRTA：基于低秩张量分解的大语言模型高效参数微调方法 large language model
3 Large Language Models can Achieve Social Balance 利用大型语言模型实现社会平衡，探索智能体交互中的群体关系涌现 large language model
4 Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models 提出可扩展的监狱突破攻击以解决大型语言模型的安全漏洞 large language model
5 Toxic Subword Pruning for Dialogue Response Generation on Large Language Models 提出ToxPrune方法，通过剪枝LLM中的有害子词，提升对话生成安全性与多样性。 large language model
6 A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models 提出学习率路径切换训练范式，高效更新大语言模型版本。 large language model
7 BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired Prompts BloomWise：利用布鲁姆分类学提示增强大语言模型的问题解决能力 large language model
8 Neuron-Level Sequential Editing for Large Language Models 提出神经元级序列编辑方法NSE，解决LLM多轮知识更新中的遗忘与失效问题 large language model ✅
9 A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models 提出一种免训练免提示的中文拼写纠错方法，利用大语言模型作为纯语言模型。 large language model
10 On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models 研究揭示大型语言模型在浪漫关系预测中存在的性别和种族偏见 large language model
11 Mechanistic Behavior Editing of Language Models 提出TaRot方法，通过可学习旋转矩阵干预LLM神经回路，提升小样本学习性能。 large language model ✅
12 Correlation-Aware Select and Merge Attention for Efficient Fine-Tuning and Context Length Extension 提出相关性感知选择与合并注意力机制，高效微调并扩展LLM上下文长度。 large language model
13 LongGenBench: Long-context Generation Benchmark 提出LongGenBench，用于评估大型语言模型在长文本生成任务中的性能 large language model
14 From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression 提出R2C模型，利用多文档阅读器进行提示压缩，提升大语言模型性能。 large language model
15 ECon: On the Detection and Resolution of Evidence Conflicts 提出ECon以解决证据冲突检测与处理问题 large language model
16 AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text 提出创造力指数以量化语言模型的创造力，通过系统地将机器文本归因于网络文本。 large language model
17 Consistent Autoformalization for Constructing Mathematical Libraries 提出一致性自动形式化方法，提升数学库构建的可靠性 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🔗⭐
18 DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech 提出DiDOTS，利用知识蒸馏和参数高效微调，对转录语音中的痴呆症信息进行混淆处理。 teacher-student distillation large language model
19 Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks 提出自校正学习框架SCL，提升视觉语言模型在推理任务中的性能 DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页