{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pointer-guided-pre-training-infusing-large","title":"Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness","arxiv_id":"2406.04156","date":"2024-06-06","proceeding":null,"authors":["Lars Hillebrand","Prabhupad Pradhan","Christian Bauckhage","Rafet Sifa"],"abstract":"We introduce \"pointer-guided segment ordering\" (SO), a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations in large language models. Our methodology leverages a self-attention-driven pointer network to restore the original sequence of shuffled text segments, addressing the challenge of capturing the structural coherence and contextual dependencies within documents. This pre-training approach is complemented by a fine-tuning methodology that incorporates dynamic sampling, augmenting the diversity of training instances and improving sample efficiency for various downstream applications. We evaluate our method on a diverse set of datasets, demonstrating its efficacy in tasks requiring sequential text classification across scientific literature and financial reporting domains. Our experiments show that pointer-guided pre-training significantly enhances the model's ability to understand complex document structures, leading to state-of-the-art performance in downstream classification tasks.","url_abs":"https://arxiv.org/abs/2406.04156v1","url_pdf":"https://arxiv.org/pdf/2406.04156v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pointer-guided-pre-training-infusing-large","repo_url":"https://github.com/LarsHill/pointer-guided-pre-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"set","method_name":"SET"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}