# Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation

arXiv: https://arxiv.org/abs/2609.32839 · HTML: https://mlsanity.com/paper/2609.32839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Learning Disentangled Representations for Recommendation](https://mlsanity.com/paper/1910.14238/) (2019)
- [Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation](https://mlsanity.com/paper/2206.06003/) (2022)
- [CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems](https://mlsanity.com/paper/2401.07521/) (2024)
- [DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias](https://mlsanity.com/paper/2208.05190/) (2022)
- [Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time](https://mlsanity.com/paper/2406.07932/) (2024)
- [Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment](https://mlsanity.com/paper/2305.05585/) (2023)
- [Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework](https://mlsanity.com/paper/2306.17426/) (2023)
- [Understanding and Modeling Passive-Negative Feedback for Short-video Sequential Recommendation](https://mlsanity.com/paper/2308.04086/) (2023)
- [Latent User Intent Modeling for Sequential Recommenders](https://mlsanity.com/paper/2211.09832/) (2022)
- [AlignPxtr: Aligning Predicted Behavior Distributions for Bias-Free Video Recommendations](https://mlsanity.com/paper/2503.06920/) (2025)
- [Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation](https://mlsanity.com/paper/2508.11086/) (2025)
- [Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation](https://mlsanity.com/paper/2308.08120/) (2023)

## Abstract (arXiv)

Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from different underlying states, such as genuine enjoyment, passive consumption, or inattention. The challenge is especially acute in short-form video, where watch-based signals are strongly affected by measurement confounders such as video duration - the same watch time can imply different levels of preference for videos of different lengths, while ratio-based metrics can systematically favor short videos. As a result, optimizing raw engagement can amplify measurement artifacts rather than improving user value. We propose a Factorized Latent Value Model (FLVM) for measuring user preference from heterogeneous behavioral feedback. The model treats observed behaviors as noisy measurements of a low-dimensional, factorized latent value state and uses structured output heads to model heterogeneous feedback signals. A restricted baseline path captures predictable variation from measurement-confounding features such as video duration, user propensity, and session context, while a routed latent path estimates preference-relevant value advantage. The resulting latent value score can be integrated into an existing recommender system as a ranking feature or ranking score. On YouTube Shorts, a major short-form video platform, this model improves offline metrics and lifts a primary viewer enjoyment metric by 2.67% in online A/B tests.