# EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline

arXiv: https://arxiv.org/abs/2504.03598 · HTML: https://mlsanity.com/paper/2504.03598/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 14 of 14)

- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [Answering Questions by Meta-Reasoning over Multiple Chains of Thought](https://mlsanity.com/paper/2304.13007/) (2023)
- [Arctic-Embed 2.0: Multilingual Retrieval Without Compromise](https://mlsanity.com/paper/2412.04506/) (2024)
- [BEAVER: An Enterprise Benchmark for Text-to-SQL](https://mlsanity.com/paper/2409.02038/) (2024)
- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval](https://mlsanity.com/paper/2404.09889/) (2024)
- [Guiding Retrieval using LLM-based Listwise Rankers](https://mlsanity.com/paper/2501.09186/) (2025)
- [Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method](https://mlsanity.com/paper/2501.18539/) (2025)
- [BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search](https://mlsanity.com/paper/2408.06643/) (2024)

## Built on by (most cited first, 15 of 15)

- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [RL-Index: Reinforcement Learning for Retrieval Index Reasoning](https://mlsanity.com/paper/2606.16316/) (2026)
- [PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing](https://mlsanity.com/paper/2508.11116/) (2025)
- [Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts](https://mlsanity.com/paper/2510.22956/) (2025)
- [Utilizing Metadata for Better Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.11863/) (2026)
- [CORE-T: COherent REtrieval of Tables for Text-to-SQL](https://mlsanity.com/paper/2601.13111/) (2026)
- [Fine-Grained Table Retrieval Through the Lens of Complex Queries](https://mlsanity.com/paper/2603.07146/) (2026)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [Xetrieval: Mechanistically Explaining Dense Retrieval](https://mlsanity.com/paper/2605.29507/) (2026)
- [SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing](https://mlsanity.com/paper/2606.11424/) (2026)
- [CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval](https://mlsanity.com/paper/2606.28365/) (2026)
- [Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers](https://mlsanity.com/paper/2609.00844/) (2026)
- [MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval](https://mlsanity.com/paper/2609.01316/) (2026)
- [Self-Evolving Search Index](https://mlsanity.com/paper/2609.19656/) (2026)
- [ExperienceIndex: Artifact-Grounded Memory](https://mlsanity.com/paper/2610.10091/) (2026)

## Abstract (arXiv)

Existing information retrieval systems excel in cases where the language of target documents closely matches that of the user query. However, real-world retrieval systems are often required to implicitly reason whether a document is relevant. For example, when retrieving technical texts or tables, their relevance to the user query may be implied through a particular jargon or structure, rather than explicitly expressed in their content. Large language models (LLMs) hold great potential in identifying such implied relevance by leveraging their reasoning skills. Nevertheless, current LLM-augmented retrieval is hindered by high latency and computation cost, as the LLM typically computes the query-document relevance online, for every query anew. To tackle this issue we introduce EnrichIndex, a retrieval approach which instead uses the LLM offline to build semantically-enriched retrieval indices, by performing a single pass over all documents in the retrieval corpus once during ingestion time. Furthermore, the semantically-enriched indices can complement existing online retrieval approaches, boosting the performance of LLM re-rankers. We evaluated EnrichIndex on five retrieval tasks, involving passages and tables, and found that it outperforms strong online LLM-based retrieval systems, with an average improvement of 11.7 points in recall @ 10 and 10.6 points in NDCG @ 10 compared to strong baselines. In terms of online calls to the LLM, it processes 293.3 times fewer tokens which greatly reduces the online latency and cost. Overall, EnrichIndex is an effective way to build better retrieval indices offline by leveraging the strong reasoning skills of LLMs.