cs.CL（2024-11-18）

📊 共 23 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) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis 提出MEMO-Bench，用于评估文本到图像模型和多模态大语言模型在人类情感分析上的能力。 large language model multimodal
2 Understanding Chain-of-Thought in LLMs through Information Theory 通过信息论理解LLM中的思维链，无需标注数据即可评估中间推理步骤。 large language model chain-of-thought
3 Testing Uncertainty of Large Language Models for Physics Knowledge and Reasoning 评估大语言模型在物理知识和推理中的不确定性，揭示准确率与置信度的关系。 large language model
4 Large Language Model for Qualitative Research -- A Systematic Mapping Study 系统性综述：利用大型语言模型赋能质性研究 large language model
5 ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity ByteScience：利用自动微调LLM桥接非结构化科学文献与结构化数据 large language model
6 Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment 研究大型语言模型在道德说服下的行为，评估其易感性和伦理一致性 large language model
7 CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization CROW：通过内部一致性正则化消除大型语言模型中的后门 large language model
8 LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models 提出LP数据流水线，利用CPU高效构建特定领域的大语言模型数据集。 large language model
9 Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models 利用大型语言模型分析大学生心理健康支持的情感倾向 large language model
10 Membership Inference Attack against Long-Context Large Language Models 针对长文本大语言模型的上下文成员推理攻击，揭示隐私泄露风险 large language model
11 Large corpora and large language models: a replicable method for automating grammatical annotation 提出一种基于大语言模型的语法标注自动化方法，提升语言学研究效率。 large language model
12 ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification ZeFaV：利用大语言模型增强零样本事实核查能力 large language model
13 Popular LLMs Amplify Race and Gender Disparities in Human Mobility 大型语言模型在人类移动预测中加剧种族和性别偏见 large language model
14 FedCoLLM: A Parameter-Efficient Federated Co-tuning Framework for Large and Small Language Models FedCoLLM：面向大小语言模型的参数高效联邦协同调优框架 large language model
15 Enhancing LLM Reasoning with Reward-guided Tree Search 提出STILL-1框架，利用奖励引导的树搜索增强LLM在数学推理任务中的能力 large language model
16 Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality 提出一种基于知识图谱嵌入的LLM增强方法，以减少幻觉问题 large language model
17 Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation 提出基于检索的低资源语言翻译方法，提升LLM在少数民族语言翻译上的性能 large language model
18 Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models 提出安全雪球代理以破解大型视觉语言模型的安全性问题 multimodal ✅
19 Rethinking Thinking Tokens: Understanding Why They Underperform in Practice 分析性思考令牌（Thinking Tokens）在语言模型推理中表现不佳的原因 chain-of-thought
20 VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs VersaTune：一种高效的数据组合框架，用于训练多能力大型语言模型 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🔗⭐
21 Bi-Mamba: Towards Accurate 1-Bit State Space Models 提出Bi-Mamba，一种高效的1-bit状态空间模型，提升大语言模型训练和部署效率。 Mamba SSM state space model ✅
22 Benchmarking pre-trained text embedding models in aligning built asset information 构建资产信息对齐基准，评估预训练文本嵌入模型在领域知识对齐中的性能。 representation learning large language model
23 Learning to Ask: Conversational Product Search via Representation Learning 提出ConvPS模型，通过表征学习实现对话式产品搜索，提升用户购物体验。 representation learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页