Authority-Aware GraphRAG for Explainable Tax-Risk Evidence Retrieval: A Controlled Evaluation of Typed Legal Graph Expansion
DOI:
https://doi.org/10.54097/ex1zaj80Keywords:
GraphRAG, tax-law retrieval, knowledge graphs, explainable AI, provenance, evidence selection, synthetic benchmark.Abstract
Tax-risk analysis needs evidence sets that include a governing provision, companion rules, and a visible relationship path, rather than a single high-scoring passage. We study the retrieval stage of graph-grounded tax analysis through an executable, controlled benchmark. Building on citation-graph expansion used in tax-oriented retrieval systems, we propose Typed Evidence-Budgeted GraphRAG (TEB-GraphRAG), which jointly scores lexical seeds, relation types, and a deterministic sparse two-topic gate while preserving graph-path provenance. A transparent synthetic collection contains 59 real tax-section identifiers with researcher-authored synopses, 238 researcher-authored directed relations, and 700 templated issue descriptions; 500 held-out queries are scored without learned retriever training. On this benchmark, our method reaches 85.40% Recall@5, versus 69.27% for unrestricted one-hop graph expansion and 59.93% for BM25. The 16.13-point advantage over graph expansion has a topic-cluster bootstrap 95% interval of [11.37, 21.60] points. Under type-label permutation on a balanced 200-case stress subset, mean Recall@5 drops to 0.597; an unrelated-topic distractor reduces full-test recall to 0.636. Typed retrieval therefore depends strongly on metadata fidelity and query focus. These controlled findings do not establish legal correctness, tax-risk classification, or LLM answer quality.
Downloads
References
[1] Lewis, P., Perez, E., Piktus, A., Petroni, F., Galkin, A., Goyal, N., Ott, M., Grave, E., Lample, G., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474. https://arxiv.org/abs/2005.11401.
[2] Robertson, S., & Zaragoza, H. (2009). The probabilistic relevance framework: BM25 and beyond. Foundations and Trends in Information Retrieval, 4(1–2), 1–174. https://doi.org/10.1561/1500000019
[3] Edge, D., Truong, H., Miller, B., & Gokhale, A. (2024). From local to global: A Graph RAG approach to query-focused summarization. https://arxiv.org/abs/2404.16130
[4] Yue, X., & Zhu, R. (2024). An explainable hybrid machine learning framework for cash-flow-conditioned multi-horizon liquidity risk early warning: An SME-oriented benchmark study. World Journal of Management Science, 2(1), 63–72.
[5] Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., & Androutsopoulos, I. (2020). LEGAL-BERT: The Muppets straight out of Law School. Findings of the Association for Computational Linguistics: EMNLP 2020, 2898–2904. https://doi.org/10.18653/v1/2020.findings-emnlp.261
[6] Chalkidis, I., Manginas, A., Katakis, E., Kotsis, G., Aletras, N., & Androutsopoulos, I. (2022). LexGLUE: A benchmark dataset for legal language understanding in English. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 4310–4330. https://doi.org/10.18653/v1/2022.acl-long.297
[7] Guha, N., Block, S., Wang, J., Martin, M., Hirst, G., Ho, D., Grisham, C., & Mitchell, T. (2023). LegalBench: A collaboratively built benchmark for measuring legal reasoning in large language models. Advances in Neural Information Processing Systems, 36. https://doi.org/10.52202/075280-1915
[8] Shao, Y., Mao, J., Liu, Y., He, Y., Yan, R., Zhang, M., & Ma, S. (2020). BERT-PLI: Modeling paragraph-level interactions for legal case retrieval. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 3501–3507. https://doi.org/10.24963/ijcai.2020/484
[9] Karpukhin, V., Oguz, B., Min, S., Lyu, X., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781. https://doi.org/10.18653/v1/2020.emnlp-main.550
[10] Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 3982–3992. https://doi.org/10.18653/v1/D19-1410
[11] Zhu, X., Xie, Y., Liu, Y., Li, Y., & Hu, W. (2025). Knowledge graph-guided retrieval augmented generation. Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 8912–8924. https://doi.org/10.18653/v1/2025.naacl-long.449
[12] Zhou, F. (2026). Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders. Innovation and Technology Studies, 3(1), 27–41.
[13] Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., & Manning, C. D. (2024). RAPTOR: Recursive abstractive processing for tree-organized retrieval. Proceedings of the International Conference on Learning Representations.
[14] Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. Proceedings of the International Conference on Learning Representations.
[15] Wang, J., Ge, Y., Liu, J., & Jiang, B. (2024). Early warning of liquidity stress in U.S. banks with seasonally aligned frailty hazards and delayed-feedback conformal alarms. Journal of Trends in Finance and Economics, 1(1), 85–100.
[16] Gao, L., Schulman, J., Hilton, J., Madaan, A., Kim, Y., Rao, N., Szlam, A., & Wu, J. (2023). RARR: Researching and revising what language models say, using language models. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 16477–16508. https://doi.org/10.18653/v1/2023.acl-long.910
[17] Min, S., Lyu, X., Holtzman, A., Artetxe, M., Lewis, M., Hajishirzi, H., & Zettlemoyer, L. (2023). FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 12076–12100. https://doi.org/10.18653/v1/2023.emnlp-main.741
[18] Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. Proceedings of the International Conference on Learning Representations.
[19] Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017). Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. https://arxiv.org/abs/1701.06538
[20] Fedus, W., Zoph, B., & Shazeer, N. (2022). Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research, 23(120), 1–39.
[21] Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Chen, W., & Chen, Z. (2022). LoRA: Low-rank adaptation of large language models. Proceedings of the International Conference on Learning Representations. https://arxiv.org/abs/2106.09685
[22] Johnson, J., Douze, M., & Jégou, H. (2021). Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3), 535–547. https://doi.org/10.1109/TBDATA.2019.2921572
[23] Cormack, G. V., Clarke, C. L. A., & Büttcher, S. (2009). Reciprocal rank fusion outperforms Condorcet and individual rank learning methods. Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 758–759. https://doi.org/10.1145/1571941.1572114
[24] Teng, D. (2025). TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows. World Journal of Engineering Research, 3(6), 55–66.
[25] Tan, Y., Wu, B., Cao, J., & Jiang, B. (2025). LLaMA-UTP: Knowledge-guided expert mixture for analyzing uncertain tax positions. IEEE Access, 13, 90637–90650. https://doi.org/10.1109/ACCESS.2025.3571502
[26] Zhao, W., Chen, T., Wang, B., & Shen, Z. (2026). PIPE-RAG: An execution-guided retrieval and reuse framework for reliable machine learning pipeline code generation. WEP Transactions on Computer Science and Intelligent Systems Research, 13, 286–297.
[27] Rhee, M., Kim, J., Park, S., & Lee, J. (2026). Enhancing Web search agents with self-play contrastive fine-tuning. IEEE Access. https://doi.org/10.1109/ACCESS.2026.3717594
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Law and Society
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
