sandylaker/ib-edl

Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025)

37
/ 100
Emerging

This helps data scientists and machine learning engineers fine-tune large language models (LLMs) for multiple-choice question answering. It takes a pre-trained LLM and a dataset like OBQA, producing a more reliable model that can also identify when it's being asked questions outside its training scope. This is for professionals building and deploying AI assistants or automated Q&A systems.

No commits in the last 6 months.

Use this if you need to fine-tune an LLM for classification tasks like multiple-choice QA and want to ensure its predictions are well-calibrated and it can detect out-of-distribution questions.

Not ideal if your task involves open-ended text generation, as this implementation is currently limited to classification-style question answering.

large-language-models question-answering model-calibration out-of-distribution-detection AI-safety
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

4

Language

Python

License

MIT

Last pushed

Mar 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sandylaker/ib-edl"

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