通过从隐式反馈中去噪虚假兴趣改进个性化标题生成
Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback
AI总结：
针对历史点击流中噪声导致标题幻觉的问题，提出PHG-DIF框架，通过双阶段过滤去除点击噪声并结合多级时间融合建模用户兴趣，同时发布DT-PENS基准数据集，在标题生成任务上达到SOTA。
摘要：
准确的个性化标题生成取决于从历史行为中精确捕捉用户兴趣。然而，现有方法忽略了整个历史点击流中与个性化无关的点击噪声，这可能导致偏离真实用户偏好的幻觉标题。本文通过在用户和新闻两个维度的严谨分析，揭示了点击噪声对个性化生成质量的不利影响。基于这些洞察，我们提出了一种通过从隐式反馈中去噪虚假兴趣的个性化标题生成框架（PHG-DIF）。PHG-DIF首先采用双阶段过滤，有效移除以短停留时间和异常点击突增为特征的点击流噪声，然后利用多级时间融合来动态建模用户不断演变的多方面兴趣，以实现精准画像。此外，我们发布了DT-PENS，这是一个新的基准数据集，包含1,000名精心筛选用户的点击行为，以及近10,000条带有历史停留时间标注的个性化标注标题。大量实验表明，PHG-DIF显著减轻了点击噪声的不利影响并大幅提升了标题质量，在DT-PENS上取得了最先进（SOTA）的结果。我们的框架实现和数据集可在https://github.com/liukejin-up/PHG-DIF获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
