Summary of Retrieval-augmented Generation For Domain-specific Question Answering: a Case Study on Pittsburgh and Cmu, by Haojia Sun et al.
Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
by Haojia Sun, Yaqi Wang, Shuting Zhang
First submitted to arxiv on: 20 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Retrieval-Augmented Generation (RAG) system aims to enhance large language models’ ability to answer domain-specific questions by providing them with relevant documents. The system extracts subpages using a greedy scraping strategy and employs a hybrid annotation process, combining manual and Mistral-generated question-answer pairs. The RAG framework integrates BM25 and FAISS retrievers, enhanced with a reranker for improved document retrieval accuracy. Experimental results show that the RAG system outperforms a non-RAG baseline, particularly in time-sensitive and complex queries, with significant improvements in F1 score and recall. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a special system to help big language models find answers to specific questions about Pittsburgh and Carnegie Mellon University. They took lots of web pages and made them into smaller sections, then used a mix of human-made and computer-generated questions and answers to teach the system how to work. The new system uses two different ways to search for relevant documents and another step to make sure it finds the best ones. When they tested it, the RAG system did much better than the old way, especially when answering tricky or time-sensitive questions. |
Keywords
» Artificial intelligence » F1 score » Rag » Recall » Retrieval augmented generation
