Topical-Chat

BIG-bench Topical-Chat evaluates open-domain response generation in conversations grounded in topical information.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.

Category	generation
Subcategory	open-domain dialogue
Page status	active
Metric	BLEU
Direction	higher_is_better
Unit	score
Dataset size	22295
Publisher	Google BIG-bench

What it measures

The task asks a model to generate a response in an open-domain conversation. Its examples contain multi-turn dialogue about topics such as people, science, sports, and culture.

Task format

Dialogue context followed by a generated response.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub