Parameter-efficient fine-tuning (PEFT) methods address the challenge of fine-tuning large language models (LLMs) for specific downstream tasks when the cost of training all model parameters becomes prohibitive. Fine-tuning large language models with billions of parameters can be computationally expensive, require significant storage, and lead to overfitting, especially when adapting to
Retrieval-augmented generation (RAG) improves the large language model's (LLM) response by using external data to enhance the relevance and accuracy of their outputs. Instead of relying only on pre-trained knowledge, RAG allows models to fetch and integrate information from external sources, such as vector databases. This approach is
Original Paper: https://arxiv.org/abs/2310.06839 By: Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu Abstract: In long context scenarios, large language models (LLMs) face three main challenges: higher computational/financial cost, longer latency, and inferior performance. Some studies reveal that the
Original Paper: https://arxiv.org/abs/2309.11495 By: Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston Abstract: Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate
In this blog, we’ll explore how DoorDash leverages Retrieval-Augmented Generation (RAG) to address Dashers’ queries using insights from the company’s internal blogs. We’ll conduct practical experiments based on the techniques discussed in DoorDash’s Tech blog, utilizing a curated DoorDash dataset. We will use Athina AI which
Language models like GPT-4 have established themselves as the leading standard in the NLP industry for developing advanced applications. These models can perform diverse tasks and easily adapt to new tasks using Prompt Engineering Techniques. However, they also present a massive challenge around training and fine-tuning. Due to their massive
Large language models (LLMs), such as GPT-3 and LaMDA, are at the forefront of natural language processing (NLP). Trained on terabytes of text data, they generate human-like text and power multiple applications, including chatbots, virtual assistants, and search engines. This initial training process, where the LLM learns general language representations
Retrieval-augmented generation (RAG) is a significant advancement in the ability of large language models (LLMs) to utilize external knowledge for more accurate and contextually rich responses. However, in standard RAG systems, small text chunks are used to isolate precise information for retrieval. This approach works well for focused facts but
The Retrieval Augmented Generation (RAG) technique enhances the capabilities of large language models (LLMs) by grounding their responses in external knowledge sources. This approach improves the accuracy and relevance of LLM outputs, especially when dealing with domain-specific topics. Traditional RAG systems retrieve a single document to inform responses. While effective
Introduction In the quickly changing technology landscape of today, artificial intelligence (AI) is a game-changer for companies in a wide range of industries. But what is the hidden energy source for these clever systems? The foundation of contemporary AI applications, AI infrastructure, holds the key to the solution. What is
After completing the development and validation phase, model deployment is the next important step in the LLMOps workflow. Successful deployment requires careful consideration of efficiency, scalability, and the specific needs of the deployment environment. Quantization: Optimization Technique for Efficient Deployment of LLMs Quantization is a technique used to reduce LLMs&
Managing large language models (LLMs) through LLMOps workflows requires a structured approach to ensure effective development, deployment, and maintenance. These workflows are divided into several key phases: data collection, model development, deployment, and governance, each crucial to the performance and sustainability of LLM systems. Specific methodologies, tools, and best practices
research-papers
Original Paper: https://arxiv.org/abs/2408.16984 By: Tan Zhi-Xuan, Micah Carroll, Matija Franklin, Hal Ashton Abstract: The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences
research-papers
Original Paper: https://arxiv.org/abs/2408.01262 By: Kunlun Zhu, Yifan Luo, Dingling Xu, Ruobing Wang, Shi Yu, Shuo Wang, Yukun Yan, Zhenghao Liu, Xu Han, Zhiyuan Liu, Maosong Sun Abstract: Retrieval-Augmented Generation (RAG) systems have demonstrated their advantages in alleviating the hallucination of Large Language Models (LLMs). Existing
research-papers
Original Paper: https://arxiv.org/pdf/2408.11796 By: Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov Abstract We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B
research-papers
Original Paper: https://arxiv.org/abs/2408.12599 By: Xun Liang, Hanyu Wang, Yezhaohui Wang, Shichao Song, Jiawei Yang, Simin Niu, Jie Hu, Dan Liu, Shunyu Yao, Feiyu Xiong, Zhiyu Li Abstract: In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated high text generation quality. However, in real-world
research-papers
Original Paper: https://arxiv.org/pdf/2402.03367 Code Sample: https://github.com/NirDiamant/RAG_Techniques/blob/main/all_rag_techniques/fusion_retrieval.ipynb RAG-Fusion or Fusion-retrieval RAG, is an advanced technique that enhances the traditional Retrieval Augmented Generation (RAG) approach used in AI and natural language processing. This method
research-papers
Original Papers: * Query Rewriting: https://arxiv.org/pdf/2305.14283 * Step-back Prompting: https://arxiv.org/abs/2310.06117 * Sub-query Decomposition: https://arxiv.org/pdf/2404.00610 Code Sample: https://github.com/NirDiamant/RAG_Techniques/blob/main/all_rag_techniques/query_transformations.ipynb Query transformations are advanced techniques used to enhance
research-papers
Code Sample: https://github.com/NirDiamant/RAG_Techniques/blob/main/all_rag_techniques/reranking.ipynb Reranking is a powerful technique used in Retrieval-Augmented Generation (RAG) systems to refine and improve the relevance of retrieved documents. Here's a detailed explanation of reranking methods in RAG systems, along with their
research-papers
Original Paper: https://arxiv.org/abs/2408.09416 By: Hongyin Zhu Abstract: This paper carefully summarizes extensive and profound questions from all walks of life, focusing on the current high-profile AI field, covering multiple dimensions such as industry trends, academic research, technological innovation and business applications. This paper meticulously curates
research-papers
Original Paper: https://arxiv.org/abs/2408.10615 By: Ming Jiang, Tingting Huang, Biao Guo, Yao Lu, Feng Zhang Abstract: In recent years, Large language models (LLMs) have garnered significant attention due to their superior performance in complex reasoning tasks. However, recent studies may diminish their reasoning capabilities markedly when
research-papers
Original Paper: https://arxiv.org/abs/2408.01262 By: Kunlun Zhu, Yifan Luo, Dingling Xu, Ruobing Wang, Shi Yu, Shuo Wang, Yukun Yan, Zhenghao Liu, Xu Han, Zhiyuan Liu, Maosong Sun Abstract: Retrieval-Augmented Generation (RAG) systems have demonstrated their advantages in alleviating the hallucination of Large Language Models (LLMs). Existing
research-papers
Original Paper: https://arxiv.org/abs/2408.08067 By: Dongyu Ru, Lin Qiu, Xiangkun Hu, Tianhang Zhang, Peng Shi, Shuaichen Chang, Cheng Jiayang, Cunxiang Wang, Shichao Sun, Huanyu Li, Zizhao Zhang, Binjie Wang, Jiarong Jiang, Tong He, Zhiguo Wang, Pengfei Liu, Yue Zhang, Zheng Zhang Abstract Despite Retrieval-Augmented Generation (RAG)
research-papers
Original Paper: https://arxiv.org/abs/2408.08921 By: Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, Siliang Tang Abstract Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external