A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment
This addresses challenges in question answering for users needing more reliable and ethically aligned AI responses, though it appears incremental as it builds on existing RAG methods.
The paper tackles the problem of improving global understanding and aligning responses with human preferences in retrieval-augmented generation for question answering by proposing GraphMPA, a graph-based framework with mode-seeking preference alignment, which demonstrates effectiveness across six datasets.
Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist in achieving global understanding and aligning responses with human ethical and quality preferences. To address these issues, we propose GraphMPA, a comprehensive graph-based framework with mode-seeking preference alignment. Our approach constructs a hierarchical document graph using a general similarity measurement, mimicking human cognitive processes for information understanding and synthesis. Additionally, we introduce mode-seeking preference optimization to better align model outputs with human preferences through probability-matching constraints. Extensive experiments on six datasets demonstrate the effectiveness of our \href{https://github.com/tangquanwei/GraphMPA}{GraphMPA}.