cs.CL（2024-07-22）

📊 共 19 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) (18 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Leveraging Large Language Models to Geolocate Linguistic Variations in Social Media Posts	利用大型语言模型进行社交媒体帖子中语言变体的地理定位	large language model	✅
2	Multimodal Input Aids a Bayesian Model of Phonetic Learning	提出基于多模态信息的贝叶斯语音学习模型，提升语音辨别能力	multimodal
3	Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability	研究表明，大型语言模型在组合任务上表现出能力差异，复杂推理任务仍具挑战。	large language model	✅
4	Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research	构建WaterER基准，评估大语言模型在水工程与研究领域的应用潜力	large language model
5	An Empirical Study of Retrieval Augmented Generation with Chain-of-Thought	提出RAFT方法，结合CoT、SFT和RAG，提升生成式对话模型在复杂问题上的性能。	chain-of-thought
6	LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models	LLaST：利用大型语言模型改进端到端语音翻译系统	large language model	✅
7	Impacts of Anthropomorphizing Large Language Models in Learning Environments	探讨LLM拟人化对学习环境的影响，为提升教学效果奠定基础	large language model
8	Knowledge Mechanisms in Large Language Models: A Survey and Perspective	综述大型语言模型中的知识机制，分析利用、演化及潜在问题	large language model
9	Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models	Imposter.AI：提出针对对齐大语言模型的隐蔽意图对抗攻击方法	large language model
10	ALLaM: Large Language Models for Arabic and English	ALLaM：面向阿拉伯语和英语的大型语言模型，提升多语言环境下的性能。	large language model
11	Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias	提出视角转换提示（PeT）方法，有效降低大语言模型生成内容中的毒性和偏见	large language model
12	Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation	提出RMBoost以提升奖励模型的合成数据生成质量	large language model
13	Multilingual Fine-Grained News Headline Hallucination Detection	提出了一个多语言、细粒度的新闻标题幻觉检测数据集，并探索了监督微调和上下文学习方法。	large language model
14	dMel: Speech Tokenization made Simple	提出dMel：一种简化的语音Token化方法，提升语音合成与识别性能。	large language model
15	Counter Turing Test ($CT^2$): Investigating AI-Generated Text Detection for Hindi -- Ranking LLMs based on Hindi AI Detectability Index ($ADI_{hi}$)	针对印地语AI生成文本检测，提出反图灵测试($CT^2$)框架与印地语AI可检测性指数($ADI_{hi}$)，并评估多种LLM。	large language model	✅
16	Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners	提出奇异值对角扩展与跨层学习，提升LLM量化精度并降低计算开销	large language model
17	Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service	构建可靠、快速、通用的LLM幻觉检测与缓解服务	large language model
18	Dissecting Multiplication in Transformers: Insights into LLMs	剖析Transformer乘法运算：揭示LLM在算术任务中的局限性与改进方法	large language model

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

#	题目	一句话要点	标签	🔗	⭐
19	Can GPT-4 learn to analyse moves in research article abstracts?	利用GPT-4自动分析研究论文摘要中的“Move”结构，提升文本分析效率。	affordance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页