# A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment

Source: [A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment](<https://www.sota2.com/research/paper/68fa798e1e209131cea7e321>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:00:46.441Z

Authors: Quanwei Tang, Sophia Yat Mei Lee, Junshuang Wu, Dong Zhang, Shoushan Li, Erik Cambria, Guodong Zhou

Published: 2025-06-22T09:08:44.000Z

## Abstract

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}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.17951>)

[PDF](<https://arxiv.org/pdf/2506.17951.pdf>)