CAP-LLM：用于新闻标题生成的上下文增强个性化大型语言模型
CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation
AI总结：
针对个性化新闻标题生成中用户兴趣捕捉和事实一致性的挑战，提出CAP-LLM框架，通过用户偏好编码器、上下文注入适配器和对比损失强化模块，在PENS数据集上取得最优性能，平衡个性化与事实准确性。
摘要：
在信息过载的时代，个性化新闻标题生成对于通过根据用户偏好定制内容同时准确传达新闻事实来吸引用户至关重要。现有方法难以有效捕捉复杂的用户兴趣并确保事实一致性，常常导致标题泛泛而谈或具有误导性。利用大型语言模型（LLMs）在文本生成方面前所未有的能力，我们提出了上下文增强个性化LLM（CAP-LLM），这是一种新颖的框架，将用户偏好和事实一致性约束整合到一个强大的预训练LLM骨干中。CAP-LLM具有用户偏好编码器以捕捉长期用户兴趣，上下文注入适配器以将这些偏好和当前文章上下文无缝整合到LLM的生成过程中，以及事实一致性强化模块，采用新颖的对比损失来减轻幻觉。在真实世界的PENS数据集上评估，CAP-LLM在所有指标上均达到最先进的性能。值得注意的是，它在事实一致性（FactCC为87.50）方面显著优于BART（86.67）等强基线，同时增强了个性化（Pc(avg) 2.73，Pc(max) 17.25）和内容覆盖率（ROUGE-1 26.55，ROUGE-2 9.95，ROUGE-L 23.01）。我们的消融研究、人工评估和敏感性分析进一步验证了每个组件的有效性和我们方法的鲁棒性，展示了CAP-LLM在新闻标题生成中实现个性化与事实准确性之间优越平衡的能力。
英文摘要：
In the era of information overload, personalized news headline generation is crucial for engaging users by tailoring content to their preferences while accurately conveying news facts. Existing methods struggle with effectively capturing complex user interests and ensuring factual consistency, often leading to generic or misleading headlines. Leveraging the unprecedented capabilities of Large Language Models (LLMs) in text generation, we propose Context-Augmented Personalized LLM (CAP-LLM), a novel framework that integrates user preferences and factual consistency constraints into a powerful pre-trained LLM backbone. CAP-LLM features a User Preference Encoder to capture long-term user interests, a Context Injection Adapter to seamlessly integrate these preferences and current article context into the LLM's generation process, and a Fact-Consistency Reinforcement Module employing a novel contrastive loss to mitigate hallucination. Evaluated on the real-world PENS dataset, CAP-LLM achieves state-of-the-art performance across all metrics. Notably, it significantly improves factual consistency (FactCC of 87.50) over strong baselines like BART (86.67), while simultaneously enhancing personalization (Pc(avg) 2.73, Pc(max) 17.25) and content coverage (ROUGE-1 26.55, ROUGE-2 9.95, ROUGE-L 23.01). Our ablation studies, human evaluations, and sensitivity analyses further validate the effectiveness of each component and the robustness of our approach, demonstrating CAP-LLM's ability to achieve a superior balance between personalization and factual accuracy in news headline generation.
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。
