# Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos

arXiv: https://arxiv.org/abs/2502.07327 · HTML: https://mlsanity.com/paper/2502.07327/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [A Dataset for Movie Description](https://mlsanity.com/paper/1501.02530/) (2015)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Measuring Fairness in Ranked Outputs](https://mlsanity.com/paper/1610.08559/) (2016)
- [Neural Retrievers are Biased Towards LLM-Generated Content](https://mlsanity.com/paper/2310.20501/) (2023)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration](https://mlsanity.com/paper/2405.16546/) (2024)
- [Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images](https://mlsanity.com/paper/2311.14084/) (2023)
- [Non-Imaging Medical Data Synthesis for Trustworthy AI: A Comprehensive Survey](https://mlsanity.com/paper/2209.09239/) (2022)
- [On Measuring Bias in Online Information](https://mlsanity.com/paper/1704.05730/) (2017)
- [New Fairness Metrics for Recommendation that Embrace Differences](https://mlsanity.com/paper/1706.09838/) (2017)

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

- [DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage](https://mlsanity.com/paper/2603.01106/) (2026)
- [Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval](https://mlsanity.com/paper/2602.10833/) (2026)

## Abstract (arXiv)

With the rapid development of AI-generated content (AIGC), the creation of high-quality AI-generated videos has become faster and easier, resulting in the Internet being flooded with all kinds of video content. However, the impact of these videos on the content ecosystem remains largely unexplored. Video information retrieval remains a fundamental approach for accessing video content. Building on the observation that retrieval models often favor AI-generated content in ad-hoc and image retrieval tasks, we investigate whether similar biases emerge in the context of challenging video retrieval, where temporal and visual factors may further influence model behavior. To explore this, we first construct a comprehensive benchmark dataset containing both real and AI-generated videos, along with a set of fair and rigorous metrics to assess bias. This benchmark consists of 13,000 videos generated by two state-of-the-art open-source video generation models. We meticulously design a suite of rigorous metrics to accurately measure this preference, accounting for potential biases arising from the limited frame rate and suboptimal quality of AIGC videos. We then applied three off-the-shelf video retrieval models to perform retrieval tasks on this hybrid dataset. Our findings reveal a clear preference for AI-generated videos in retrieval. Further investigation shows that incorporating AI-generated videos into the training set of retrieval models exacerbates this bias. Unlike the preference observed in image modalities, we find that video retrieval bias arises from both unseen visual and temporal information, making the root causes of video bias a complex interplay of these two factors. To mitigate this bias, we fine-tune the retrieval models using a contrastive learning approach. The results of this study highlight the potential implications of AI-generated videos on retrieval systems.