Graph-Augmented Retrieval and Uncertainty Estimation for Explainable Scientific Question Answering
Keywords:
scientific question answering; graph-augmented retrieval; uncertainty estimation; retrieval-augmented generation; explainable artificial intelligence; knowledge graphs; trustworthy systems; socio-technical infrastructure; research infrastructure; algorithmic governanceAbstract
Scientific question answering increasingly relies on large language models and retrieval-augmented generation, but scientific domains demand more than fluent answers. They require provenance, calibrated uncertainty, and explanations that reflect evolving evidence. This paper examines graph-augmented retrieval and uncertainty estimation as complementary architectural strategies for explainable scientific question answering. It argues that knowledge graphs and structured scientific resources can improve retrieval precision, contextual grounding, and traceability, while uncertainty estimation can signal when an answer should be trusted, revised, or deferred. The paper develops a system-level analysis of trade-offs involving graph construction, hybrid retrieval, latency, storage, governance, and sustainability. It considers how graph augmentation expands explainability by exposing relational evidence paths but also introduces maintenance burdens, coverage gaps, and bias risks. It further examines uncertainty estimation methods such as verbalized confidence, calibration, and conformal prediction, noting that they must be integrated into user interfaces, auditing routines, and risk controls rather than treated as isolated model outputs. Through cross-domain comparisons in biomedicine, climate science, materials science, and policy research, the paper shows that scientific question answering is a socio-technical infrastructure. Successful deployment depends not only on model accuracy but also on institutional accountability, data stewardship, equitable access, and robust evaluation. The conclusion proposes design principles for graph-augmented, uncertainty-aware scientific question answering systems that balance performance with transparency, fairness, and long-term sustainability.
References
1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
2. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M. (2020). Retrieval augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning (Vol. 119, pp. 3929–3938). PMLR.
3. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (pp. 6769–6781). Association for Computational Linguistics.
4. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (pp. 874–880). Association for Computational Linguistics.
5. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J. B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, L., Jones, C., Cassirer, A., ... Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. In Proceedings of the 39th International Conference on Machine Learning (Vol. 162, pp. 2206–2240). PMLR.
6. Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), 1–38.
7. Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., & Liu, T. (2023). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv. https://arxiv.org/abs/2311.05232
8. Zhang, R. (2025, December). Uncertainty-Aware RAG: Trustworthy Generation and Risk Control. In 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF) (pp. 526-531). IEEE.
9. Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Hatfield-Dodds, Z., DasSarma, N., Tran-Johnson, E., Johnston, S., El-Showk, S., Jones, A., Elhage, N., Hume, T., Chen, A., Bai, Y., Bowman, S., Fort, S., ... Kaplan, J. (2022). Language models (mostly) know what they know. arXiv. https://arxiv.org/abs/2207.05221
10. Lin, S., Hilton, J., & Evans, O. (2022). Teaching models to express their uncertainty in words. arXiv. https://arxiv.org/abs/2205.14334
11. Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (Vol. 70, pp. 1321–1330). PMLR.
12. Angelopoulos, A. N., & Bates, S. (2021). A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv. https://arxiv.org/abs/2107.07511
13. Hogan, A., Blomqvist, E., Cochez, M., d’Amato, C., de Melo, G., Gutierrez, C., Kirrane, S., Labra Gayo, J. E., Navigli, R., Ngomo, A.-C. N., Polleres, A., Rashid, S. M., Rula, A., Schmelzeisen, L., Sequeda, J., Staab, S., & Zimmermann, A. (2021). Knowledge graphs. ACM Computing Surveys, 54(4), 1–37.
14. Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2021). A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2), 494–514.
15. Wang, Q., Mao, Z., Wang, B., & Guo, L. (2017). Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 29(12), 2724–2743.
16. Petroni, F., Piktus, A., Fan, A., Lewis, P., Yazdani, M., De Cao, N., Thorne, J., Jernite, Y., Karpukhin, V., Maillard, J., Plachouras, V., Rocktäschel, T., & Riedel, S. (2021). KILT: A benchmark for knowledge intensive language tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 2523–2544). Association for Computational Linguistics.
17. Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018). FEVER: A large-scale dataset for fact extraction and verification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 809–819). Association for Computational Linguistics.
18. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N., Chen, A., Creel, K., Davis, J. Q., Demszky, D., ... Liang, P. (2021). On the opportunities and risks of foundation models. arXiv. https://arxiv.org/abs/2108.07258
19. Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P. S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., Biles, C., Brown, S., Kenton, Z., Hawkins, W., Stepleton, T., Birhane, A., Hendricks, L. A., Rimell, L., Isaac, W., ... Gabriel, I. (2022). Taxonomy of risks posed by language models. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (pp. 214–229). Association for Computing Machinery.
20. Raji, I. D., Smart, A., White, R. N., Mitchell, M., Gebru, T., Hutchinson, B., Smith-Loud, J., Theron, D., & Barnes, P. (2020). Closing the AI accountability gap: Defining an end-to-endframework for internal algorithmic auditing. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (pp. 33-44). Association for Computing Machinery.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Computer Science and Engineering Transactions
This work is licensed under a Creative Commons Attribution 4.0 International License.