fladhak

creative-summ-data

contrastive_error_attribution

effective-faithfulness

Code for the "Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization" paper

pretraining_biases

Wikilingua

Multilingual abstractive summarization dataset extracted from WikiHow.

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

Wikilingua

Multilingual abstractive summarization dataset extracted from WikiHow.

context-compression

novel-chapter-lists

Novel Chapter Dataset

scripts

SCRIPTS summarization system for IARPA MATERIAL project.

fladhak/contrastive_error_attribution

fladhak/pretraining_biases

fladhak/creative-summ-data

fladhak/effective-faithfulness

Code for the "Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization" paper

fladhak/Wikilingua

Multilingual abstractive summarization dataset extracted from WikiHow.