# An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

arXiv: https://arxiv.org/abs/2509.26225 · HTML: https://mlsanity.com/paper/2509.26225/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 30 Sep 2025.

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics](https://mlsanity.com/paper/2403.14077/) (2024)
- [Rethinking Attention-Model Explainability through Faithfulness Violation Test](https://mlsanity.com/paper/2201.12114/) (2022)
- [Explainable Video Action Reasoning via Prior Knowledge and State Transitions](https://mlsanity.com/paper/1908.10700/) (2019)
- [Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification](https://mlsanity.com/paper/2105.02657/) (2021)
- [EVAL: Explainable Video Anomaly Localization](https://mlsanity.com/paper/2212.07900/) (2022)
- [Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networks](https://mlsanity.com/paper/2002.00367/) (2020)
- [Discrete neural representations for explainable anomaly detection](https://mlsanity.com/paper/2112.05585/) (2021)
- [Why is plausibility surprisingly problematic as an XAI criterion?](https://mlsanity.com/paper/2303.17707/) (2023)
- [Causalainer: Causal Explainer for Automatic Video Summarization](https://mlsanity.com/paper/2305.00455/) (2023)
- [T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers](https://mlsanity.com/paper/2403.04523/) (2024)
- [Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples](https://mlsanity.com/paper/2502.03957/) (2025)
- [An Integrated Framework for Multi-Granular Explanation of Video Summarization](https://mlsanity.com/paper/2405.10082/) (2024)

## Abstract (arXiv)

In this paper, we present our experimental study on generating plausible textual explanations for the outcomes of video summarization. For the needs of this study, we extend an existing framework for multigranular explanation of video summarization by integrating a SOTA Large Multimodal Model (LLaVA-OneVision) and prompting it to produce natural language descriptions of the obtained visual explanations. Following, we focus on one of the most desired characteristics for explainable AI, the plausibility of the obtained explanations that relates with their alignment with the humans' reasoning and expectations. Using the extended framework, we propose an approach for evaluating the plausibility of visual explanations by quantifying the semantic overlap between their textual descriptions and the textual descriptions of the corresponding video summaries, with the help of two methods for creating sentence embeddings (SBERT, SimCSE). Based on the extended framework and the proposed plausibility evaluation approach, we conduct an experimental study using a SOTA method (CA-SUM) and two datasets (SumMe, TVSum) for video summarization, to examine whether the more faithful explanations are also the more plausible ones, and identify the most appropriate approach for generating plausible textual explanations for video summarization.