---
title: "Discussion on \"The Query Expansion That Made Retrieval Worse\" | Hashnode"
description: "Discussion on \"The Query Expansion That Made Retrieval Worse\". Term expansion is a lexical trick. Feed it to a dense encoder and you drag the query off the answer."
url: "https://hashnode.com/posts/the-query-expansion-that-made-retrieval-worse/6a9577229fdc6d2137cb225f"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [The Query Expansion That Made Retrieval Worse](https://expensivetobewrong.hashnode.dev/the-query-expansion-that-made-retrieval-worse?utm_source=hashnode&utm_medium=feed)

Term expansion is a lexical trick. Feed it to a dense encoder and you drag the query off the answer.

Aug 31 · 12 min read · expensivetobewrong.hashnode.dev  
Read the article

-   [#rag](https://hashnode.com/tag/rag)
-   [#embeddings](https://hashnode.com/tag/embeddings)
-   [#nlp](https://hashnode.com/tag/nlp)
-   [#information-retrival](https://hashnode.com/tag/information-retrival)
-   [#vectorsearch](https://hashnode.com/tag/vectorsearch)

## Written by

[Abhijat](https://hashnode.com/@abhijat)

@abhijat · Delhi, India

  
[View profile](https://hashnode.com/@abhijat)

The most consequential numbers in an ML system are the ones nobody tuned.

Engineer working on retrieval and evaluation for LLM systems. I write Expensive To Be Wrong, a blog about the numbers those systems report and the defaults nobody actually chose: why your hybrid search is closer to a voting machine than a ranker, why an accuracy with no error bar is an anecdote with a decimal point, and when a system should just say "I don't know." Mostly arithmetic you can redo with a calculator, and experiments you can run in an afternoon.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.