Agentic RAG

Does Fine-Tuning Models in Specific Domains Make Sense? A Case Study of BioRAG

by
Does Fine-Tuning Models in Specific Domains Make Sense? A Case Study of BioRAG

BioRAG: A RAG-LLM Framework for Biological Question Reasoning The question-answering systems in the life sciences face challenges such as rapid discovery, evolving insights, and complex interactions of knowledge entities, necessitating a comprehensive knowledge base and precise retrieval. To address this, we introduce BioRAG, a retrieval-augmented generation framework that combines large language models. First, we parse, … Read more

ACL 2024: Cambridge Team Open Sources Pre-trained Multi-modal Retriever

by
ACL 2024: Cambridge Team Open Sources Pre-trained Multi-modal Retriever

Follow our public account to discover the beauty of CV technology This article shares the ACL 2024 paper PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers, open-sourced by the Cambridge University team, empowering multi-modal large model RAG applications, and is the first pre-trained general multi-modal late-interaction knowledge retriever. Paper link: https://arxiv.org/abs/2402.08327 Project homepage: https://preflmr.github.io/ Introduction The … Read more

BIORAG: A Breakthrough Framework for Biological Question Reasoning

by
BIORAG: A Breakthrough Framework for Biological Question Reasoning

Source: Biological Large Models This article is approximately 3000 words long and is suggested to be read in 5 minutes. This article introduces an innovative biological question reasoning system that combines Retrieval-Augmented Generation (RAG) and Large Language Models (LLM). In today’s rapidly advancing life sciences field, efficiently processing and answering complex biological questions has always … Read more

Professor E Wei Nan’s New Work: Memory3 in Large Models

by
Professor E Wei Nan's New Work: Memory3 in Large Models

Reported by Machine Heart Editor: Chen Chen A 2.4B Memory3 outperforms larger LLM and RAG models. According to a message from the WeChat public account of Machine Heart: In recent years, large language models (LLMs) have gained unprecedented attention due to their extraordinary performance. However, the training and inference costs of LLMs are high, and … Read more

Visualizing FAISS Vector Space and Adjusting RAG Parameters to Improve Result Accuracy

by
Visualizing FAISS Vector Space and Adjusting RAG Parameters to Improve Result Accuracy

Source: DeepHub IMBA This article is approximately 3600 words long, and it is recommended to read it in 7 minutes. In this article, we will use the visualization library renumics-spotlight to visualize the multi-dimensional embeddings of the FAISS vector space in 2-D, and explore the possibility of improving the accuracy of RAG responses by changing … Read more

Performance Improvement with Pseudo-Graph Indexing for RAG

by
Performance Improvement with Pseudo-Graph Indexing for RAG

This article is approximately 5500 words long and is recommended for an 11-minute read. This paper proposes a pseudo-graph structure by relaxing the pattern constraints on data and relationships in traditional KGs. Paper Title: Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning Author Affiliation: Renmin University of China (RUC), Shanghai … Read more

Enhancing RAG Capabilities with Knowledge Graphs to Reduce LLM Hallucinations

by
Enhancing RAG Capabilities with Knowledge Graphs to Reduce LLM Hallucinations

Source: DeepHub IMBA This article is approximately 2600 words long and is recommended to be read in 8 minutes. For hallucinations in large language models (LLM), knowledge graphs have proven to be superior to vector databases. When using large language models (LLMs), hallucination is a common issue. LLMs generate fluent and coherent text but often … Read more

FaaF: A Custom Fact Recall Evaluation Framework for RAG Systems

by
FaaF: A Custom Fact Recall Evaluation Framework for RAG Systems

Source: DeepHub IMBA This article is about 1000 words long and is recommended to read in 5 minutes. When real information exceeds a few words, the chance of exact matching becomes too slim. In RAG systems, actual fact recall evaluation may face the following issues: There has not been much attention paid to automatically verifying … Read more

ACL2024 | LLM+RAG May Destroy Information Retrieval: An In-Depth Study

by
ACL2024 | LLM+RAG May Destroy Information Retrieval: An In-Depth Study

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP master’s and doctoral students, university teachers, and corporate researchers. The Vision of the Community is to promote communication and progress between the academic community, industry, and enthusiasts in machine learning and natural language processing, especially for beginners. … Read more

Live Broadcast: Large Model + Knowledge Base (RAG) for Industry Digitalization

by
Live Broadcast: Large Model + Knowledge Base (RAG) for Industry Digitalization

In the blink of an eye, 2024 is nearing its end. This year, the “Huawei Expert Live Room” has successfully held 7 live broadcasts, sharing Huawei’s experience in industry digital transformation, covering construction, steel, non-ferrous metals, smelting, transportation, oil and gas, and continuously shaping the brand image of “digital transformation partners”. Recently, some friends commented … Read more