# Building Multimodal AI Chatbots

arXiv: https://arxiv.org/abs/2305.03512 · HTML: https://mlsanity.com/paper/2305.03512/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 21 Apr 2023.

## Builds on (most cited first, 20 of 20)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons](https://mlsanity.com/paper/1909.03087/) (2019)
- [Image Chat: Engaging Grounded Conversations](https://mlsanity.com/paper/1811.00945/) (2018)
- [Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation](https://mlsanity.com/paper/1701.08251/) (2017)
- [PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling](https://mlsanity.com/paper/2108.01453/) (2021)
- [Multimodal Dialogue Response Generation](https://mlsanity.com/paper/2110.08515/) (2021)
- [Achieving Reliable Human Assessment of Open-Domain Dialogue Systems](https://mlsanity.com/paper/2203.05899/) (2022)

## Built on by (most cited first, 2 of 2)

- [Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models](https://mlsanity.com/paper/2401.00127/) (2023)
- [Enhancing Higher Education with Generative AI: A Multimodal Approach for Personalised Learning](https://mlsanity.com/paper/2502.07401/) (2025)

## Abstract (arXiv)

This work aims to create a multimodal AI system that chats with humans and shares relevant photos. While earlier works were limited to dialogues about specific objects or scenes within images, recent works have incorporated images into open-domain dialogues. However, their response generators are unimodal, accepting text input but no image input, thus prone to generating responses contradictory to the images shared in the dialogue. Therefore, this work proposes a complete chatbot system using two multimodal deep learning models: an image retriever that understands texts and a response generator that understands images. The image retriever, implemented by ViT and BERT, selects the most relevant image given the dialogue history and a database of images. The response generator, implemented by ViT and GPT-2/DialoGPT, generates an appropriate response given the dialogue history and the most recently retrieved image. The two models are trained and evaluated on PhotoChat, an open-domain dialogue dataset in which a photo is shared in each session. In automatic evaluation, the proposed image retriever outperforms existing baselines VSE++ and SCAN with Recall@1/5/10 of 0.1/0.3/0.4 and MRR of 0.2 when ranking 1,000 images. The proposed response generator also surpasses the baseline Divter with PPL of 16.9, BLEU-1/2 of 0.13/0.03, and Distinct-1/2 of 0.97/0.86, showing a significant improvement in PPL by -42.8 and BLEU-1/2 by +0.07/0.02. In human evaluation with a Likert scale of 1-5, the complete multimodal chatbot system receives higher image-groundedness of 4.3 and engagingness of 4.3, along with competitive fluency of 4.1, coherence of 3.9, and humanness of 3.1, when compared to other chatbot variants. The source code is available at: https://github.com/minniie/multimodal_chat.git.