Domain-Adaptive Retrieval-Augmented Generation for Scientific Literature Understanding
Keywords:
domain adaptation, retrieval-augmented generation, scientific literature, information retrieval, socio-technical systems, governance, robustness, sustainability, fairness, infrastructureAbstract
Scientific literature understanding presents distinctive challenges for retrieval-augmented generation because scientific corpora are heterogeneous, rapidly changing, and deeply structured by disciplinary conventions. This paper examines domain-adaptive retrieval-augmented generation as a socio-technical architecture rather than a single modeling technique. It argues that effective systems must coordinate domain-aware indexing, adaptive retrieval, evidence fusion, generation control, evaluation, governance, and long-term infrastructure maintenance. The analysis begins with the foundations of retrieval-augmented generation and then considers why scientific domains require specialized adaptation across terminology, citation networks, experimental reporting, and multimodal evidence. It discusses architectural trade-offs among sparse and dense retrieval, unified and federated semantic spaces, parametric and non-parametric memory, latency and accuracy, and local adaptation and centralized governance. The paper also examines fairness, robustness, sustainability, and policy implications, including the risks of uneven disciplinary coverage, opaque provenance, energy-intensive inference, and inequitable access. It proposes that domain-adaptive systems should be evaluated not only by answer accuracy but also by evidentiary traceability, calibration, update resilience, disciplinary representativeness, and operational sustainability. The conclusion emphasizes that scientific retrieval-augmented generation will succeed only if it is treated as governed infrastructure supporting reproducible and accountable knowledge work.
References
1. Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610-623.
2. Beltagy, I., Lo, K., & Cohan, A. (2019). SciBERT: A pretrained language model for scientific text. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 3615-3620.
3. 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. Proceedings of the 39th International Conference on Machine Learning, 2206-2240.
4. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv. https://arxiv.org/abs/2312.10997
5. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M.-W. (2020). Retrieval augmented language model pre-training. Proceedings of the 37th International Conference on Machine Learning, 3929-3938.
6. Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low-rank adaptation of large language models. International Conference on Learning Representations.
7. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 874-880.
8. Izacard, G., Lewis, P., Lomeli, M., Hosseini, L., Petroni, F., Schick, T., Dwivedi-Yu, J., Joulin, A., Riedel, S., & Grave, E. (2023). Atlas: Few-shot learning with retrieval augmented language models. Journal of Machine Learning Research, 24(251), 1-43.
9. Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769-6781.
10. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Kuttler, H., Lewis, M., Yih, W.-t., Rocktaschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459-9474.
11. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. Proceedings of the Conference on Fairness, Accountability, and Transparency, 220-229.
12. Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020). Green AI. Communications of the ACM, 63(12), 54-63.
13. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645-3650.
14. Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W. W., Salakhutdinov, R., & Manning, C. D. (2018). HotpotQA: A dataset for diverse, explainable multi-hop question answering. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2369-2380.
15. Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020). BioBERT: A pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 36(4), 1234-1240.
16. Bender, E. M., & Friedman, B. (2018). Data statements for natural language processing: Toward mitigating system bias and enabling better science. Transactions of the Association for Computational Linguistics, 6, 587-604.
17. Deng, Q., Liu, S., Qiu, H., Long, N., Lin, W., & Chen, S. (2026, April). Unified Semantic Space and Attention-Based Fusion Framework for Multi-Source Heterogeneous Retrieval-Augmented Generation. In 2026 6th International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) (pp. 591-597). IEEE.
18. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2024). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. International Conference on Learning Representations.
19. Lewis, P., Oguz, B., Rinott, R., Riedel, S., & Schwenk, H. (2020). MLQA: Evaluating cross-lingual extractive question answering. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 7315-7330.
20. 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. Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, 214-229.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
