mlsanityData to 14 Oct 2026

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

arXiv 2506.17951 ↗First posted 22 Jun 2025cs.CLcited by 5

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

also in 1 more
Abstract (arXiv)

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 hrefhttps://github.com/tangquanwei/GraphMPAGraphMPA.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 44 references that are in the map. First posted on arXiv 22 Jun 2025.

Builds on

27 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  3. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 24

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2017Deep reinforcement learning from human preferencescited by 3,912
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  11. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  12. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
12 more
  1. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  2. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
  3. 2024Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferencecited by 501
  4. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  6. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  7. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 208
  8. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 184
  9. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  10. 2018ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Taskscited by 67
  11. 2021RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledgecited by 61
  12. 2024Reward-RAG: Enhancing RAG with Reward Driven Supervisioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelscited by 3
  2. 2025Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspectivecited by 0
  3. 2026PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generationcited by 0
  4. 2026Relative Time Intervals Representation for Word-level Timestamping with Masked Trainingcited by 0
  5. 2026Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
  2. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
  3. 2025DSRAG: A Domain-Specific Retrieval Framework Based on Document-derived Multimodal Knowledge Graph
  4. 2026The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs
  5. 2025BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
  6. 2025Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
  7. 2025In-depth Analysis of Graph-based RAG in a Unified Framework
  8. 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation