declare-lab/CICERO

The purpose of this repository is to introduce new dialogue-level commonsense inference datasets and tasks. We chose dialogues as the data source because dialogues are known to be complex and rich in commonsense.

35
/ 100
Emerging

Introduces two annotated dialogue datasets with complementary difficulty levels: CICERO-v1 with single inferences per context for generative and multiple-choice tasks, and CICERO-v2 with multiple plausible inferences (multiview) to challenge models on reasoning diversity. Provides DIALeCT, a dialogue-level transformer model for contextual commonsense inference generation, available on Hugging Face with interactive demo. Targets NLP researchers working on commonsense reasoning, dialogue understanding, and instruction-following capabilities in language models.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

64

Forks

7

Language

Python

License

MIT

Last pushed

Mar 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/declare-lab/CICERO"

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