Anup Jadhav
Anup Jadhav
Learn. Teach. Grow.
⌘K
Subscribe Sign in
Anup Jadhav

Data in CSV Format Isn’t Always the Best for LLMs

Anup Jadhav

by Anup Jadhav

When you feed a large table into an LLM, the way you format the input can change the model’s accuracy quite a bit. In a test of 11 formats (CSV, JSON, markdown table, YAML and more), a markdown “key: value” style scored around 60.7 % accuracy, which was far ahead of CSV at roughly 44.3 %. CSV and JSONL, despite being the usual defaults, were among the weakest performers.

What stood out to me was the trade off. The top format used many more tokens, so you have to balance cost and accuracy. For anyone working with agents, retrieval systems or table data, sticking with CSV by default might be leaving performance on the table. It is worth experimenting with different formats. Read the full article

Subscribe to The AI Engineering Brief

No spam, no sharing to third party. Only you and me.

More like this

Prompt Engineering vs Context Engineering

From Anthropic: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents Prompt Engineering: Prompt engineering refers to methods for writing and organizing LLM

Why LLMs Confidently Hallucinate a Seahorse Emoji That Never Existed

Ask any major AI if there's a seahorse emoji and they'll say yes with 100% confidence.

Goodbye Manual Prompts, Hello DSPy

Today I learned about a smarter way to deal with the headache of prompts in production. Drew Brunig’s talk

Nemawashi (根回し)

There’s a Japanese concept called nemawashi (literally “root-walking”) that offers a way around the dreaded “big reveal” in engineering

AI agents are starting to do real work

Ethan Mollick argues that AIs have quietly crossed a line. OpenAI recently tested models on complex, expert-designed tasks that usually

Choosing Between RAG, Fine-Tuning, or Hybrid Approaches for LLMs

A structured guide for AI engineers making architecture decisions