Salvato in:
Dettagli Bibliografici
Autori principali: Shah, Keyush, Goyal, Abhishek, Wasserman, Isaac
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.03754
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909338174488576
author Shah, Keyush
Goyal, Abhishek
Wasserman, Isaac
author_facet Shah, Keyush
Goyal, Abhishek
Wasserman, Isaac
contents Retrieval augmented generation (RAG) has become the standard in long context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embeddings are most similar to that of the query are deemed most relevant. This has consequences in subjective QA tasks, where the most relevant text may not directly contain the answer. In this work, we propose a novel extension to RAG systems, which we call Retrieval from AI Derived Documents (RAIDD). RAIDD leverages the full power of the LLM in the retrieval process by deriving inferred features, such as summaries and example questions, from the documents at ingest. We demonstrate that this approach significantly improves the performance of RAG systems on long-context QA tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03754
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Retrieval in QA Systems with Derived Feature Association
Shah, Keyush
Goyal, Abhishek
Wasserman, Isaac
Computation and Language
Information Retrieval
Retrieval augmented generation (RAG) has become the standard in long context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embeddings are most similar to that of the query are deemed most relevant. This has consequences in subjective QA tasks, where the most relevant text may not directly contain the answer. In this work, we propose a novel extension to RAG systems, which we call Retrieval from AI Derived Documents (RAIDD). RAIDD leverages the full power of the LLM in the retrieval process by deriving inferred features, such as summaries and example questions, from the documents at ingest. We demonstrate that this approach significantly improves the performance of RAG systems on long-context QA tasks.
title Enhancing Retrieval in QA Systems with Derived Feature Association
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2410.03754