# Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs

arXiv: https://arxiv.org/abs/2408.04331 · HTML: https://mlsanity.com/paper/2408.04331/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Good News, Everyone! Context driven entity-aware captioning for news images](https://mlsanity.com/paper/1904.01475/) (2019)
- [Transform and Tell: Entity-Aware News Image Captioning](https://mlsanity.com/paper/2004.08070/) (2020)
- [Bias of AI-Generated Content: An Examination of News Produced by Large Language Models](https://mlsanity.com/paper/2309.09825/) (2023)
- [Visually-Aware Context Modeling for News Image Captioning](https://mlsanity.com/paper/2308.08325/) (2023)
- [Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia](https://mlsanity.com/paper/2209.10474/) (2022)
- [Framing the News:From Human Perception to Large Language Model Inferences](https://mlsanity.com/paper/2304.14456/) (2023)
- ["Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning](https://mlsanity.com/paper/2306.00931/) (2023)
- [Harnessing Business and Media Insights with Large Language Models](https://mlsanity.com/paper/2406.06559/) (2024)
- [The COVID That Wasn't: Counterfactual Journalism Using GPT](https://mlsanity.com/paper/2210.06644/) (2022)
- [A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)](https://mlsanity.com/paper/2406.19054/) (2024)

## Built on by (most cited first, 1 of 1)

- [LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content](https://mlsanity.com/paper/2410.15308/) (2024)

## Abstract (arXiv)

Large language models (LLMs) and large multimodal models (LMMs) have significantly impacted the AI community, industry, and various economic sectors. In journalism, integrating AI poses unique challenges and opportunities, particularly in enhancing the quality and efficiency of news reporting. This study explores how LLMs and LMMs can assist journalistic practice by generating contextualised captions for images accompanying news articles. We conducted experiments using the GoodNews dataset to evaluate the ability of LMMs (BLIP-2, GPT-4v, or LLaVA) to incorporate one of two types of context: entire news articles, or extracted named entities. In addition, we compared their performance to a two-stage pipeline composed of a captioning model (BLIP-2, OFA, or ViT-GPT2) with post-hoc contextualisation with LLMs (GPT-4 or LLaMA). We assess a diversity of models, and we find that while the choice of contextualisation model is a significant factor for the two-stage pipelines, this is not the case in the LMMs, where smaller, open-source models perform well compared to proprietary, GPT-powered ones. Additionally, we found that controlling the amount of provided context enhances performance. These results highlight the limitations of a fully automated approach and underscore the necessity for an interactive, human-in-the-loop strategy.