{"ID":2870837,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19336","arxiv_id":"2509.19336","title":"Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation","abstract":"Large Language Models (LLMs) have demonstrated strong performance in open-ended generation tasks. However, they often struggle to adapt content to users with differing cognitive capacities, leading to a phenomenon we term cognitive misalignment. This issue arises in two forms: knowledge-level misalignment, where content is too complex or too simplistic relative to user understanding, and presentation-style misalignment, where the structure or tone hinders effective comprehension. To address these challenges, we propose the Cognitive-Level Alignment Framework (CLAF), a general-purpose generation framework that aligns both knowledge complexity and presentation style with user cognition. CLAF integrates a capability-aware retrieval module based on a hierarchical knowledge graph and a style optimization module guided by Bloom's taxonomy and preference learning. Additionally, a knowledge-controllable generation component ensures consistency and relevance throughout the output. To support training and evaluation, we construct SCALE, a cognitively annotated dataset containing responses at multiple comprehension levels per query. Empirical results show that CLAF enhances the adaptability and informativeness of LLM outputs across a range of user profiles, offering a robust solution to cognitive-level alignment in real-world applications.","short_abstract":"Large Language Models (LLMs) have demonstrated strong performance in open-ended generation tasks. However, they often struggle to adapt content to users with differing cognitive capacities, leading to a phenomenon we term cognitive misalignment. This issue arises in two forms: knowledge-level misalignment, where conten...","url_abs":"https://arxiv.org/abs/2509.19336","url_pdf":"https://arxiv.org/pdf/2509.19336v1","authors":"[\"Qingsong Wang\",\"Tao Wu\",\"Wang Lin\",\"Yueying Feng\",\"Gongsheng Yuan\",\"Chang Yao\",\"Jingyuan Chen\"]","published":"2025-09-15T10:11:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}