# Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations

arXiv: https://arxiv.org/abs/2212.04231 · HTML: https://mlsanity.com/paper/2212.04231/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [Movie Description](https://mlsanity.com/paper/1605.03705/) (2016)

## Built on by (most cited first, 6 of 6)

- [Large Language Models are Visual Reasoning Coordinators](https://mlsanity.com/paper/2310.15166/) (2023)
- [DeViL: Decoding Vision features into Language](https://mlsanity.com/paper/2309.01617/) (2023)
- [The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems](https://mlsanity.com/paper/2406.19170/) (2024)
- [From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation](https://mlsanity.com/paper/2311.12391/) (2023)
- [VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework](https://mlsanity.com/paper/2502.00711/) (2025)
- [WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification](https://mlsanity.com/paper/2603.18752/) (2026)

## Abstract (arXiv)

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single datasets. We propose to evade these limitations by applying recent advances in large-scale multi-task pretraining of generative Transformer models to the problem of VL-NLE tasks. Our approach outperforms recent models by a large margin, with human annotators preferring the generated explanations over the ground truth in two out of three evaluated datasets. As a novel challenge in VL-NLE research, we propose the problem of multi-task VL-NLE and show that jointly training on multiple tasks can increase the explanation quality. We discuss the ethical implications of high-quality NLE generation and other issues in recent VL-NLE research.