QuOTE: Question-Oriented Text Embeddings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917924666605568 |
|---|---|
| author | Neeser, Andrew Latimer, Kaylen Khatri, Aadyant Latimer, Chris Ramakrishnan, Naren |
| author_facet | Neeser, Andrew Latimer, Kaylen Khatri, Aadyant Latimer, Chris Ramakrishnan, Naren |
| contents | We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines, which rely on embedding raw text chunks, QuOTE augments chunks with hypothetical questions that the chunk can potentially answer, enriching the representation space. This better aligns document embeddings with user query semantics, and helps address issues such as ambiguity and context-dependent relevance. Through extensive experiments across diverse benchmarks, we demonstrate that QuOTE significantly enhances retrieval accuracy, including in multi-hop question-answering tasks. Our findings highlight the versatility of question generation as a fundamental indexing strategy, opening new avenues for integrating question generation into retrieval-based AI pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QuOTE: Question-Oriented Text Embeddings Neeser, Andrew Latimer, Kaylen Khatri, Aadyant Latimer, Chris Ramakrishnan, Naren Information Retrieval Artificial Intelligence Computation and Language Machine Learning H.3 We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional RAG pipelines, which rely on embedding raw text chunks, QuOTE augments chunks with hypothetical questions that the chunk can potentially answer, enriching the representation space. This better aligns document embeddings with user query semantics, and helps address issues such as ambiguity and context-dependent relevance. Through extensive experiments across diverse benchmarks, we demonstrate that QuOTE significantly enhances retrieval accuracy, including in multi-hop question-answering tasks. Our findings highlight the versatility of question generation as a fundamental indexing strategy, opening new avenues for integrating question generation into retrieval-based AI pipelines. |
| title | QuOTE: Question-Oriented Text Embeddings |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning H.3 |
| url | https://arxiv.org/abs/2502.10976 |