Which Nested Data Format Do Llms Understand Best? JSON Vs. Yaml Vs. XML Vs. Md
Posted3 months agoActive3 months ago
improvingagents.comTechstory
calmneutral
Debate
0/100
LlmsData FormatsJSONYamlXML
Key topics
Llms
Data Formats
JSON
Yaml
XML
The article compares the ability of Large Language Models (LLMs) to understand different nested data formats, including JSON, YAML, XML, and MD, sparking a discussion on the importance of data format compatibility.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
1s
Peak period
1
0-1h
Avg / period
1
Key moments
- 01Story posted
Oct 16, 2025 at 10:41 AM EDT
3 months ago
Step 01 - 02First comment
Oct 16, 2025 at 10:41 AM EDT
1s after posting
Step 02 - 03Peak activity
1 comments in 0-1h
Hottest window of the conversation
Step 03 - 04Latest activity
Oct 16, 2025 at 10:41 AM EDT
3 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45605954Type: storyLast synced: 11/17/2025, 10:09:21 AM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
(There was some good discussion on Hacker News around that here: https://news.ycombinator.com/item?id=45458455)
We often want to feed NON-TABULAR data to LLMs, though, such as typical API responses or config files.
This new work looks out how the format of such nested / hierarchical data affects how well LLMs can answer questions about it; specifically how several models get on with JSON, YAML, XML and Markdown.