Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback

TL;DR

This paper introduces PHG-DIF, a novel framework that effectively removes click noise from user data to improve personalized headline generation, supported by a new benchmark dataset and state-of-the-art experimental results.

Contribution

The paper proposes a dual-stage filtering and multi-level temporal fusion approach for noise reduction and interest modeling in personalized headline generation, along with a new dataset DT-PENS.

Findings

PHG-DIF significantly reduces click noise impact.

Achieves state-of-the-art results on DT-PENS.

Improves headline relevance and quality.

Abstract

Accurate personalized headline generation hinges on precisely capturing user interests from historical behaviors. However, existing methods neglect personalized-irrelevant click noise in entire historical clickstreams, which may lead to hallucinated headlines that deviate from genuine user preferences. In this paper, we reveal the detrimental impact of click noise on personalized generation quality through rigorous analysis in both user and news dimensions. Based on these insights, we propose a novel Personalized Headline Generation framework via Denoising Fake Interests from Implicit Feedback (PHG-DIF). PHG-DIF first employs dual-stage filtering to effectively remove clickstream noise, identified by short dwell times and abnormal click bursts, and then leverages multi-level temporal fusion to dynamically model users' evolving and multi-faceted interests for precise profiling. Moreover, we release DT-PENS, a new benchmark dataset comprising the click behavior of 1,000 carefully curated users and nearly 10,000 annotated personalized headlines with historical dwell time annotations. Extensive experiments demonstrate that PHG-DIF substantially mitigates the adverse effects of click noise and significantly improves headline quality, achieving state-of-the-art (SOTA) results on DT-PENS. Our framework implementation and dataset are available at https://github.com/liukejin-up/PHG-DIF.