Unbiased Multimodal Reranking for Long-Tail Short-Video Search

• URL: http://arxiv.org/abs/2603.24975v2
• Date: Mon, 30 Mar 2026 13:37:20 GMT
• Title: Unbiased Multimodal Reranking for Long-Tail Short-Video Search
• Abstract summary: Short-video search engine Kuaishou serves hundreds of millions of searches daily.<n>It suffers from a severe Matthew effect on long-tail queries: sparse user behavior data causes models to amplify low-quality content.<n>We propose a multimodal reranking framework, which estimates user experience without real user behavior.
• Score: 22.623171690832887
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Kuaishou serving hundreds of millions of searches daily, the quality of short-video search is paramount. However, it suffers from a severe Matthew effect on long-tail queries: sparse user behavior data causes models to amplify low-quality content such as clickbait and shallow content. The recent advancements in Large Language Models (LLMs) offer a new paradigm, as their inherent world knowledge provides a powerful mechanism to assess content quality, agnostic to sparse user interactions. To this end, we propose a LLM-driven multimodal reranking framework, which estimates user experience without real user behavior. The approach involves a two-stage training process: the first stage uses multimodal evidence to construct high-quality annotations for supervised fine-tuning, while the second stage incorporates pairwise preference optimization to help the model learn partial orderings among candidates. At inference time, the resulting experience scores are used to promote high-quality but underexposed videos in reranking, and further guide page-level optimization through reinforcement learning. Experiments show that the proposed method achieves consistent improvements over strong baselines in offline metrics including AUC, NDCG@K, and human preference judgement. An online A/B test covering 15\% of traffic further demonstrates gains in both user experience and consumption metrics, confirming the practical value of the approach in long-tail video search scenarios.

Related papers

• Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence [2.512325213832099]
  Black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation.<n>Lack of fine-grained control and reliability presents significant challenges in professional video creation.<n>We introduce the Agentic Self-Improvement" framework, which reframes video into a closed-loop, goal-directed optimization.
  arXiv  Detail & Related papers  (2026-08-12T17:35:16Z)
• Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding [98.3098451637867]
  Video-MME-v2 is a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding.<n>To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline.
  arXiv  Detail & Related papers  (2026-04-06T17:59:56Z)
• SaFRO: Satisfaction-Aware Fusion via Dual-Relative Policy Optimization for Short-Video Search [6.248205896178263]
  Multi-Task Fusion plays a pivotal role in industrial short-video search systems by aggregating heterogeneous prediction signals into a unified ranking score.<n>Existing approaches predominantly optimize for immediate engagement metrics, which often fail to align with long-term user satisfaction.<n>We propose SaFRO, a novel framework designed to optimize user satisfaction in short-video search.
  arXiv  Detail & Related papers  (2026-03-20T02:57:50Z)
• Enrich and Detect: Video Temporal Grounding with Multimodal LLMs [60.224522472631776]
  We introduce ED-VTG, a method for fine-grained video temporal grounding utilizing multi-modal large language models.<n>Our approach harnesses the capabilities of multimodal LLMs to jointly process text and video.<n>We demonstrate state-of-the-art results across various benchmarks in temporal video grounding and paragraph grounding settings.
  arXiv  Detail & Related papers  (2025-10-19T22:12:45Z)
• HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding [120.84817886550765]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos.<n>Existing human-centric benchmarks predominantly emphasize video generation quality and action recognition, while overlooking essential perceptual and cognitive abilities required in human-centered scenarios.<n>We propose a rigorously curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric video understanding.
  arXiv  Detail & Related papers  (2025-07-07T11:52:24Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation [57.34255010956452]
  This work revisits scaling with synthetic data and focuses on developing video-LLMs from a data-centric perspective.<n>We propose a data augmentation method called Sparrow, which synthesizes video-like samples from pure text instruction data.<n>Our proposed method achieves performance comparable to or even superior to that of baselines trained with significantly more samples.
  arXiv  Detail & Related papers  (2024-11-29T18:59:54Z)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs)<n>MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts.<n>It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• LLM-based Weak Supervision Framework for Query Intent Classification in Video Search [6.519428288229856]
  We introduce a novel approach that leverages large language models (LLMs) through weak supervision to automatically annotate a vast collection of user search queries. By incorporating domain knowledge via Chain of Thought and In-Context Learning, our approach leverages the labeled data to train low-latency models optimized for real-time inference.
  arXiv  Detail & Related papers  (2024-09-13T15:47:50Z)
• LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments [2.2021543101231167]
  Modern media firms require automated and efficient methods to identify content that is most engaging and appealing to users. We first investigate the ability of three pure-LLM approaches to identify the catchiest headline: prompt-based methods, embedding-based methods, and fine-tuned open-source LLMs. We then introduce the LLM-Assisted Online Learning Algorithm (LOLA), a novel framework that integrates Large Language Models (LLMs) with adaptive experimentation to optimize content delivery.
  arXiv  Detail & Related papers  (2024-06-03T07:56:58Z)
• vCLIMB: A Novel Video Class Incremental Learning Benchmark [53.90485760679411]
  We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to analyze catastrophic forgetting of deep models in video continual learning. We propose a temporal consistency regularization that can be applied on top of memory-based continual learning methods.
  arXiv  Detail & Related papers  (2022-01-23T22:14:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.