CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms

• URL: http://arxiv.org/abs/2510.10095v1
• Date: Sat, 11 Oct 2025 08:09:14 GMT
• Title: CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms
• Authors: Peiyuan Gong, Feiran Zhu, Yaqi Yin, Chenglei Dai, Chao Zhang, Kai Zheng, Wentian Bao, Jiaxin Mao, Yi Zhang,
• Abstract summary: We introduce textbfCardRewriter, a framework that incorporates domain-specific knowledge to enhance long-tail query rewriting.<n>CardRewriter substantially improves rewriting quality for queries targeting proprietary content.<n>It has been deployed on Kuaishou, one of China's largest short-video platforms, serving hundreds of millions of users daily.
• Score: 22.46507227200999
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Short-video platforms have rapidly become a new generation of information retrieval systems, where users formulate queries to access desired videos. However, user queries, especially long-tail ones, often suffer from spelling errors, incomplete phrasing, and ambiguous intent, resulting in mismatches between user expectations and retrieved results. While large language models (LLMs) have shown success in long-tail query rewriting within e-commerce, they struggle on short-video platforms, where proprietary content such as short videos, live streams, micro dramas, and user social networks falls outside their training distribution. To address this challenge, we introduce \textbf{CardRewriter}, an LLM-based framework that incorporates domain-specific knowledge to enhance long-tail query rewriting. For each query, our method aggregates multi-source knowledge relevant to the query and summarizes it into an informative and query-relevant knowledge card. This card then guides the LLM to better capture user intent and produce more effective query rewrites. We optimize CardRewriter using a two-stage training pipeline: supervised fine-tuning followed by group relative policy optimization, with a tailored reward system balancing query relevance and retrieval effectiveness. Offline experiments show that CardRewriter substantially improves rewriting quality for queries targeting proprietary content. Online A/B testing further confirms significant gains in long-view rate (LVR) and click-through rate (CTR), along with a notable reduction in initiative query reformulation rate (IQRR). Since September 2025, CardRewriter has been deployed on Kuaishou, one of China's largest short-video platforms, serving hundreds of millions of users daily.

Related papers

• Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search [16.441153527403163]
  Product retrieval is the backbone of e-commerce search, laying the foundation for high-quality ranking and user experience.<n>Despite extensive optimization for mainstream queries, existing systems still struggle with long-tail queries.<n>We propose an efficient data synthesis framework tailored to retrieval involving long-tail, knowledge-intensive queries.
  arXiv  Detail & Related papers  (2026-02-27T02:53:17Z)
• Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding [56.45689495743107]
  Vgent is a graph-based retrieval-reasoning-augmented generation framework to enhance LVLMs for long video understanding.<n>We evaluate our framework with various open-source LVLMs on three long-video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-15T19:14:58Z)
• CAViAR: Critic-Augmented Video Agentic Reasoning [90.48729440775223]
  We ask: can perception capabilities be leveraged to perform more complex video reasoning?<n>We develop a large language model agent given access to video modules as subagents or tools.<n>We show that the combination of our agent and critic achieve strong performance on datasets.
  arXiv  Detail & Related papers  (2025-09-09T17:59:39Z)
• SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis [52.050036778325094]
  We introduce SALOVA: Segment-Augmented Video Assistant, a novel video-LLM framework designed to enhance the comprehension of lengthy video content.<n>We present a high-quality collection of 87.8K long videos, each densely captioned at the segment level to enable models to capture scene continuity and maintain rich context.<n>Our framework mitigates the limitations of current video-LMMs by allowing for precise identification and retrieval of relevant video segments in response to queries.
  arXiv  Detail & Related papers  (2024-11-25T08:04:47Z)
• Beyond Relevance: Improving User Engagement by Personalization for Short-Video Search [16.491313774639007]
  We introduce $textPR2$, a novel and comprehensive solution for personalizing short-video search. Specifically, $textPR2$ leverages query-relevant collaborative filtering and personalized dense retrieval. We have achieved the most remarkable user engagement improvements in recent years.
  arXiv  Detail & Related papers  (2024-09-17T15:37:51Z)
• Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach [56.610806615527885]
  A key challenge in text-video retrieval (TVR) is the information asymmetry between video and text.<n>This paper introduces a data-centric framework to bridge this gap by enriching textual representations to better match the richness of video content.<n>We propose a query selection mechanism that identifies the most relevant and diverse queries, reducing computational cost while improving accuracy.
  arXiv  Detail & Related papers  (2024-08-14T01:24:09Z)
• MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline [24.93092798651332]
  We introduce MERLIN, a training-free pipeline that leverages Large Language Models (LLMs) for iterative feedback learning. MERLIN refines query embeddings from a user perspective, enhancing alignment between queries and video content. Experimental results on datasets like MSR-VTT, MSVD, and ActivityNet demonstrate that MERLIN substantially improves Recall@1, outperforming existing systems.
  arXiv  Detail & Related papers  (2024-07-17T11:45:02Z)
• VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos [67.78336281317347]
  Long-form understanding is complicated by the high redundancy of video data and the abundance of query-irrelevant information.<n>We propose VideoTree, a training-free framework which builds a query-adaptive and hierarchical video representation for LLM reasoning over long-form videos.
  arXiv  Detail & Related papers  (2024-05-29T15:49:09Z)
• Backtracing: Retrieving the Cause of the Query [7.715089044732362]
  We introduce the task of backtracing, in which systems retrieve the text segment that most likely caused a user query. We evaluate the zero-shot performance of popular information retrieval methods and language modeling methods. Our results show that there is room for improvement on backtracing and it requires new retrieval approaches.
  arXiv  Detail & Related papers  (2024-03-06T18:59:02Z)
• Query Rewriting for Retrieval-Augmented Large Language Models [139.242907155883]
  Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2023-05-23T17:27:50Z)

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.