Dataset Card for KILT

  Dataset Summary

KILT has been built from 11 datasets representing 5 types of tasks:

Fact-checking Entity linking Slot filling Open domain QA Dialog generation

All these datasets have been grounded in a single pre-processed Wikipedia dump, allowing for fairer and more consistent evaluation as well as enabling new task setups such as multitask and transfer learning with minimal effort. KILT also provides tools to analyze and understand the… See the full description on the dataset page: https://huggingface.co/datasets/facebook/kilt_tasks.

KILT (Knowledge Intensive Language Tasks) is a benchmark consisting of 11 datasets representing 5 types of tasks:

Fact-checking (FEVER), Entity linking (AIDA CoNLL-YAGO, WNED-WIKI, WNED-CWEB), Slot filling (T-Rex, Zero Shot RE), Open domain QA (Natural Questions, HotpotQA, TriviaQA, ELI5), Dialog generation (Wizard of Wikipedia).

All these datasets have been grounded in a single pre-processed wikipedia snapshot, allowing for fairer and more consistent evaluation as well as enabling new task setups such as multitask and transfer learning.

KILT Benchmark with Top-k Retrieval Results

This dataset is a modified version of the KILT Benchmark from the paper "KILT: a benchmark for knowledge intensive language tasks". It includes additional top-k retrieval results used in the paper "Chain-of-Retrieval Augmented Generation".

  Differences from the Original KILT Dataset

The primary difference is the addition of the context_doc_ids field. This field provides the IDs of the top-k documents retrieved during the… See the full description on the dataset page: https://huggingface.co/datasets/corag/kilt.