Evidentiality-guided Generator - Retrieval model

# 🌟 New model addition

## Model description

In this paper, we introduce Evidentiality-guided GGenerator, which incorporates evidentiality of passages---whether a passage contains correct evidence to support the output---into training the generator via multi-task learning of answer generation and evidentiality prediction for retrieval-augmented generation. Experimental results show large improvements across three knowledge intensive tasks: open question answering, fact verification and knowledge-enhanced dialogue.

## Open source status

* [x] the model implementation is available: https://github.com/AkariAsai/evidentiality_qa/tree/main/evi_gen
* [x] the model weights are available: https://github.com/AkariAsai/evidentiality_qa#fine-tuned-models
* [x] who are the authors: @AkariAsai

Happy to guide anyone who is interested through adding this model! Seems like it gives some nice improvements over RAG!

@qqaatw - maybe interesting for you ;-)

Start by reading the linked evi_gen implementation and the fine-tuned model weights referenced in the issue. Compare their model behavior with the Transformers model-integration conventions; done means the Evidentiality-guided Generator is integrated and usable in this repository.

Written by the indexing model from the issue text.