12kimih/HiCUPID

[ACL 2025] Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis

22
/ 100
Experimental

HiCUPID helps AI researchers and developers train and assess Large Language Models (LLMs) to create more personalized AI assistants. It provides a specialized dataset of conversational interactions and an automated evaluation model. This allows users to input an LLM and receive scores on how well it adapts to individual user preferences and maintains consistent personas.

No commits in the last 6 months.

Use this if you are developing or fine-tuning LLMs and need a robust way to train and benchmark their ability to act as truly personalized AI assistants.

Not ideal if you are looking for a pre-built, ready-to-deploy personalized assistant, as this is a toolkit for evaluating and improving models.

AI assistant development LLM fine-tuning conversational AI model evaluation personalization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

Apache-2.0

Last pushed

Jun 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/12kimih/HiCUPID"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.