Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling

2026-05-07

AI Summary

Traditional conversational recommender systems rely on closed “impression–click” feedback loops, which are prone to echo chamber effects and struggle to capture dynamically evolving user intents in open-world settings, often yielding recommendations biased toward popular yet generic items. To address this limitation, this work proposes the PA-Bridge framework, which leverages users’ freely typed text inputs as explicit intent signals. It introduces an adversarial distribution aligner to bridge the distributional gap between passively observed interactions and actively expressed intents, alongside a semantic discretization module that enables statistical representation and debiased training from non-ID-based textual data. Integrated with popularity-aware debiasing and large-scale streaming learning, PA-Bridge effectively disrupts harmful feedback loops. Online A/B experiments demonstrate a 0.54% increase in Feature Penetration Rate and a significant rise in user active days.

Abstract

Large Language Model (LLM)-driven conversational search is shifting information retrieval from reactive keyword matching to proactive, open-ended dialogues. In this context, Conversation Starters are widely deployed to provide personalized query recommendations that help users initiate dialogues. Conventionally, recommending these starters relies on a closed "exposure-click" loop. Yet, this feedback loop mechanism traps the system in an echo chamber where, compounded by data sparsity, it fails to capture the dynamic nature of conversational search intents shaped by the open world. As a result, the system skews towards popular but generic suggestions.In this work, we uncover an untapped paradigm shift to shatter this harmful feedback loop: harnessing user "free will" through active user expressions. Unlike traditional recommendations, conversational search empowers users to bypass menus entirely through manually typed queries. The open-world intents in active queries hold the key to breaking this loop. However, incorporating them is non-trivial: (1) there exists an inherent distribution shift between active queries and formulated starters. (2) Furthermore, the "non-ID-able" nature of open text renders traditional item-based popularity statistics ineffective for large-scale industrial streaming training. To this end, we propose Passive-Active Bridge (PA-Bridge), a novel framework that employs an adversarial distribution aligner to bridge the distributional gap between passively recommended starters and active expressions. Moreover, we introduce a semantic discretizer to enable the deployment of popularity debiasing algorithms. Online A/B tests on our platform, demonstrate that PA-Bridge significantly boosts the Feature Penetration Rate by 0.54% and User Active Days

Problem

• conversational search
• conversation starters
• feedback loop
• distribution shift
• active user expressions

Innovation

• active expression modeling
• distribution alignment
• popularity debiasing
• conversational search
• semantic discretization