# Large Language Models are Temporal and Causal Reasoners for Video Question Answering

arXiv: https://arxiv.org/abs/2310.15747 · HTML: https://mlsanity.com/paper/2310.15747/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 47 of its 74 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Just Ask: Learning to Answer Questions from Millions of Narrated Videos](https://mlsanity.com/paper/2012.00451/) (2020)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [Revisiting the "Video" in Video-Language Understanding](https://mlsanity.com/paper/2206.01720/) (2022)

## Built on by (most cited first, 30 of 51)

- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [MANTIS: Interleaved Multi-Image Instruction Tuning](https://mlsanity.com/paper/2405.01483/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA](https://mlsanity.com/paper/2406.09396/) (2024)
- [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://mlsanity.com/paper/2506.07464/) (2025)
- [Language Repository for Long Video Understanding](https://mlsanity.com/paper/2403.14622/) (2024)
- [Vamos: Versatile Action Models for Video Understanding](https://mlsanity.com/paper/2311.13627/) (2023)
- [VideoQA in the Era of LLMs: An Empirical Study](https://mlsanity.com/paper/2408.04223/) (2024)
- [VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs](https://mlsanity.com/paper/2409.20365/) (2024)
- [Understanding Long Videos with Multimodal Language Models](https://mlsanity.com/paper/2403.16998/) (2024)
- [LiveStar: Live Streaming Assistant for Real-World Online Video Understanding](https://mlsanity.com/paper/2511.05299/) (2025)
- [ViLA: Efficient Video-Language Alignment for Video Question Answering](https://mlsanity.com/paper/2312.08367/) (2023)
- [Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs](https://mlsanity.com/paper/2506.07180/) (2025)
- [A Causal Explainable Guardrails for Large Language Models](https://mlsanity.com/paper/2405.04160/) (2024)
- [Time Blindness: Why Video-Language Models Can't See What Humans Can?](https://mlsanity.com/paper/2505.24867/) (2025)
- [CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion](https://mlsanity.com/paper/2402.05889/) (2024)
- [Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models](https://mlsanity.com/paper/2410.17772/) (2024)
- [Bisecle: Binding and Separation in Continual Learning for Video Language Understanding](https://mlsanity.com/paper/2507.00469/) (2025)
- [TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning](https://mlsanity.com/paper/2402.19467/) (2024)
- [MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset](https://mlsanity.com/paper/2406.02106/) (2024)
- [Question-Answering Dense Video Events](https://mlsanity.com/paper/2409.04388/) (2024)
- [TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment](https://mlsanity.com/paper/2405.13911/) (2024)
- [Right this way: Can VLMs Guide Us to See More to Answer Questions?](https://mlsanity.com/paper/2411.00394/) (2024)
- [How Can Objects Help Video-Language Understanding?](https://mlsanity.com/paper/2504.07454/) (2025)
- [Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignment](https://mlsanity.com/paper/2410.02768/) (2024)
- [Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders](https://mlsanity.com/paper/2510.26027/) (2025)
- [ENTER: Event Based Interpretable Reasoning for VideoQA](https://mlsanity.com/paper/2501.14194/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have shown remarkable performances on a wide range of natural language understanding and generation tasks. We observe that the LLMs provide effective priors in exploiting textitlinguistic shortcuts for temporal and causal reasoning in Video Question Answering (VideoQA). However, such priors often cause suboptimal results on VideoQA by leading the model to over-rely on questions, textiti.e., textitlinguistic bias, while ignoring visual content. This is also known as `ungrounded guesses' or `hallucinations'. To address this problem while leveraging LLMs' prior on VideoQA, we propose a novel framework, Flipped-VQA, encouraging the model to predict all the combinations of langleV, Q, Arangle triplet by flipping the source pair and the target label to understand their complex relationships, textiti.e., predict A, Q, and V given a VQ, VA, and QA pairs, respectively. In this paper, we develop LLaMA-VQA by applying Flipped-VQA to LLaMA, and it outperforms both LLMs-based and non-LLMs-based models on five challenging VideoQA benchmarks. Furthermore, our Flipped-VQA is a general framework that is applicable to various LLMs (OPT and GPT-J) and consistently improves their performances. We empirically demonstrate that Flipped-VQA not only enhances the exploitation of linguistic shortcuts but also mitigates the linguistic bias, which causes incorrect answers over-relying on the question. Code is available at https://github.com/mlvlab/Flipped-VQA.