# NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

arXiv: https://arxiv.org/abs/2203.05081 · HTML: https://mlsanity.com/paper/2203.05081/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 66 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 30 of 55)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)

## Built on by (most cited first, 30 of 60)

- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2309.16292/) (2023)
- [Language Models are General-Purpose Interfaces](https://mlsanity.com/paper/2206.06336/) (2022)
- [Embodied Task Planning with Large Language Models](https://mlsanity.com/paper/2307.01848/) (2023)
- [Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning](https://mlsanity.com/paper/2310.00647/) (2023)
- [VideoCon: Robust Video-Language Alignment via Contrast Captions](https://mlsanity.com/paper/2311.10111/) (2023)
- [Towards Knowledge-driven Autonomous Driving](https://mlsanity.com/paper/2312.04316/) (2023)
- [SeD: Semantic-Aware Discriminator for Image Super-Resolution](https://mlsanity.com/paper/2402.19387/) (2024)
- [When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations](https://mlsanity.com/paper/2411.12701/) (2024)
- [Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation](https://mlsanity.com/paper/2503.19622/) (2025)
- [Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment](https://mlsanity.com/paper/2208.13628/) (2022)
- [LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2502.12359/) (2025)
- [Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks](https://mlsanity.com/paper/2308.09033/) (2023)
- [Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge](https://mlsanity.com/paper/2410.13016/) (2024)
- [DeViL: Decoding Vision features into Language](https://mlsanity.com/paper/2309.01617/) (2023)
- [S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning](https://mlsanity.com/paper/2309.02155/) (2023)
- [ChartQA-X: Generating Explanations for Visual Chart Reasoning](https://mlsanity.com/paper/2504.13275/) (2025)
- [TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation](https://mlsanity.com/paper/2307.14611/) (2023)
- [Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations](https://mlsanity.com/paper/2207.11401/) (2022)
- [Visualizing and Understanding Contrastive Learning](https://mlsanity.com/paper/2206.09753/) (2022)
- [Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach](https://mlsanity.com/paper/2407.20899/) (2024)
- [AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis](https://mlsanity.com/paper/2502.01785/) (2025)
- [Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations](https://mlsanity.com/paper/2212.04231/) (2022)
- [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)
- [Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA](https://mlsanity.com/paper/2312.13594/) (2023)
- [What could go wrong? Discovering and describing failure modes in computer vision](https://mlsanity.com/paper/2408.04471/) (2024)
- [Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations](https://mlsanity.com/paper/2308.16349/) (2023)
- [From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation](https://mlsanity.com/paper/2311.12391/) (2023)
- [Training A Small Emotional Vision Language Model for Visual Art Comprehension](https://mlsanity.com/paper/2403.11150/) (2024)
- [DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models](https://mlsanity.com/paper/2510.14741/) (2025)

## Abstract (arXiv)

Natural language explanation (NLE) models aim at explaining the decision-making process of a black box system via generating natural language sentences which are human-friendly, high-level and fine-grained. Current NLE models explain the decision-making process of a vision or vision-language model (a.k.a., task model), e.g., a VQA model, via a language model (a.k.a., explanation model), e.g., GPT. Other than the additional memory resources and inference time required by the task model, the task and explanation models are completely independent, which disassociates the explanation from the reasoning process made to predict the answer. We introduce NLX-GPT, a general, compact and faithful language model that can simultaneously predict an answer and explain it. We first conduct pre-training on large scale data of image-caption pairs for general understanding of images, and then formulate the answer as a text prediction task along with the explanation. Without region proposals nor a task model, our resulting overall framework attains better evaluation scores, contains much less parameters and is 15× faster than the current SoA model. We then address the problem of evaluating the explanations which can be in many times generic, data-biased and can come in several forms. We therefore design 2 new evaluation measures: (1) explain-predict and (2) retrieval-based attack, a self-evaluation framework that requires no labels. Code is at: https://github.com/fawazsammani/nlxgpt.