Don't classify. Hallucinate!

OpenAI's GPT-5.4-mini can classify e-commerce queries more cheaply by hallucinating fake categories and matching them to real ones via embeddings, according to a developer who shared the technique. The method avoids sending large lists of legal values, reducing token costs and bypassing structured output limits. The approach uses MiniLM embeddings to resolve invented classifications like 'Furniture / Living Room / Tables / Coffee' into the closest real Wayfair category.

Using LLMs to classify products, search queries, etc is by now boring. Yet it can still be difficult to constrains the LLM’s output to the legal vocabulary of brands, colors, categories, etc your system allows. In the Wayfair WANDS e-commerce dataset, for example, you want to classify a query like “wood coffee table” into its most appropriate category. Of which there are hundreds: Furniture / Office Furniture / Desks Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables Furniture / Living Room Furniture / Coffee Tables & End Tables / End & Side Tables Décor & Pillows / Decorative Pillows & Blankets / Throw Pillows Furniture / Bedroom Furniture / Dressers & Chests The classic way to implement this would be with structured outputs. You tell your provide it must constrain its outputs to a list of legal values. In Pydantic, you create a giant literal of legal output values: python from typing import Literal from pydantic import BaseModel, Field FullyQualifiedClassifications = Literal 'Furniture / Bedroom Furniture / Beds & Headboards / Beds', 'Furniture / Living Room Furniture / Chairs & Seating / Accent Chairs', 'Rugs / Area Rugs', ... times 500 class QueryClassification BaseModel : """ Structured representation of a search query for furniture e-commerce. Inherits keywords from the base Query model and adds category and sub-category. """ classifications: list FullyQualifiedClassifications = Field description="A possible classification for the product." response = client.responses.parse model="gpt-5.4-mini", input="Classify the query: brown coffee table", text format=QueryClassification, print response.output parsed.message Outputs: Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables This works. But there’s a way to do this a lot cheaper with small / dumb models at scale. Not to mention, there’s an upper limit you can send https://developers.openai.com/api/docs/guides/structured-outputs Luckily, there’s an easy pattern that makes LLM classification pretty seamless. Just ask a dumb LLM to invent plausible, fake classifications for your query: hallucination prompt = f""" Your task is to create novel, never seen before, furniture, home goods, or hardware classification that best fit a search query. Product classifications might look like: Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables Décor & Pillows / Decorative Pillows & Blankets / Throw Pillows Furniture / Bedroom Furniture / Dressers & Chests Kitchen & Tabletop / Kitchen Organization / Food Storage & Canisters School Furniture and Supplies / School Furniture / School Chairs & Seating / Stackable Chairs Baby & Kids / Toddler & Kids Bedroom Furniture / Kids Beds Here's the query to generate classifications for: brown coffee table Now we’re not sending the list of legal classifications. We’re instead, asking the LLM to make stuff up: response = client.responses.parse model="gpt-5.4-mini", input=hallucination prompt, text format=list str , It’ll then make up some BS that doesn’t actually exist in your real taxonomy like: Furniture / Living Room / Tables / Coffee Well that’s not very helpful. Actually it’s extremely helpful. You can now resolve that into the real vocabulary. It’s very cheap to build an in-memory set of embeddings of the REAL classifications. As I’ve done in this notebook https://colab.research.google.com/drive/1ljk72SBRuqWIijuEusCnDbhG1WAfZFcC scrollTo=RZ-hEr-CSr9T and this utility https://github.com/softwaredoug/cheat-at-search/blob/main/cheat at search/enrich/vocabulary.py . In the notebook, I compute a MiniLM embedding of every real Wayfair classification. I compute the embedding of the fake, hypothetical embedding from the LLM. I then dot product the fake embedding into the real ones to find the most similar. Producing: Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables You can give these hallucination tasks to dumb / cheap LLMs. And you don’t need to ship the schema over to the LLM every time. Upcoming events: Vectors Week Join me for Vectors Week, a series of events about vector retrieval, hybrid search, and building your own vector database.