Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Qingsong, Wu, Tao, Lin, Wang, Feng, Yueying, Yuan, Gongsheng, Yao, Chang, Chen, Jingyuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.19336
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918146583035904
author Wang, Qingsong
Wu, Tao
Lin, Wang
Feng, Yueying
Yuan, Gongsheng
Yao, Chang
Chen, Jingyuan
author_facet Wang, Qingsong
Wu, Tao
Lin, Wang
Feng, Yueying
Yuan, Gongsheng
Yao, Chang
Chen, Jingyuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation
Wang, Qingsong
Wu, Tao
Lin, Wang
Feng, Yueying
Yuan, Gongsheng
Yao, Chang
Chen, Jingyuan
Computation and Language
Artificial Intelligence
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.
title Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.19336