arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04450cs.CLcs.AI
收藏

基于本体的大型语言模型对话控制:一种轻量级框架用于受约束生成

Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation

Barbara Gendron, Gaël Guibon, Mathieu d'Aquin

AI总结:

本文提出一种轻量级框架,通过对话相关本体定义实现对LLM输出的模块化和可解释控制,通过建模关键方面作为约束并微调LLM,提升对话生成的可控性和可解释性。

摘要:

基于大型语言模型(LLMs)的对话代理近年来已成为人机交互的强大工具。然而,其黑盒性质意味着在可预测性和个性化方面存在挑战,这些挑战可通过受控生成解决。本文提出一种端到端方法,通过对话相关方面的本体定义来获得LLM输出的模块化和可解释性控制。关键方面被建模并用作约束;我们进一步微调LLM以生成相应内容。为了验证我们的方法,我们探索了两个任务,分别解决两个关键对话方面:英语水平和内容的极性配置。使用混合微调程序对七种最先进的开源对话LLM进行训练,我们表明我们的方法在更小的模型上也优于预训练基线。除了定量收益外,该框架仍然模型无关、轻量级且可解释,使可重用的控制策略能够扩展到新领域和交互目标。这种方法增强了与策略指令的一致性,并展示了本体驱动控制在对话系统中的有效性。

英文摘要:

Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight, and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.

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。

↑