跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 23 天前AI 評分45

WeFair:面向短影片搜尋個人化查詢改寫的保真度感知人類回饋對齊

WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search

AI 導讀

WeFair 以示範、偏好和驗證三階段的人類回饋,改善微信短影片搜尋的個人化查詢改寫,減少意圖偏移。離線實驗中,WeFair-2B 的整體準確度和意圖保留表現優於強基線;線上 A/B 測試中,有效影片觀看率相對提高 2.593%,查詢改寫率相對降低 2.350%。WeFair-2B 已部署於微信短影片搜尋系統,每日服務超過 100 million 次查詢。

正文

Published on Oct 30

·

Submitted by

an998

on Nov 2

Authors:

,

,

,

,

,

,

,

,

Abstract

WeFair improves personalized query rewriting via fidelity-aware human feedback stages—demonstration, preference, and verification—to reduce intent drift and boost search effectiveness in short-video platforms.

Short-video search needs compact query rewriters that recover users' personalized intent from ambiguous queries under strict latency constraints. Existing LLM-based methods have improved rewriting by using synthetic reasoning and subsequent consumption-behavioral feedback. However, overemphasizing subsequent consumption can favor engaging content over the user's immediate need, causing intent drift even when rewritten queries are grounded in behavioral history. We propose WeFair, Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in WeChat short-video search. WeFair uses human feedback according to how directly it reflects personalized intent, assigning feedback fidelity to a progression from demonstration to preference to verification. We first mine actual queries and user reformulations from search sessions, and then screen them for contextual support. In the demonstration stage, a supervised fine-tuning curriculum progresses from large-scale context-to-query learning to reasoning and direct prediction on human reformulation and preservation. In the preference stage, direct preference optimization learns relative preferences from subsequent consumption feedback. In the verification stage, group relative policy optimization rewards exact agreement with reformulation or preservation targets to constrain intent drift. Further analysis shows that broad supervision benefits the full curriculum supervised training, while strict verification achieves better performance than auxiliary rewards. In offline experiments, WeFair-2B outperforms strong rewriting baselines in overall accuracy and intent preservation. An online A/B test shows relative increases of 2.593% in effective video-view rate and a 2.350% relative reduction in query reformulation rate. WeFair-2B has been deployed in the WeChat short-video search system, which serves over 100 million queries per day.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.16927

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.16927 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.16927 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.16927 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co