Retrieval-Augmented Generation with Multi-Role LLMs for Evidence-Aware Search
Keywords:
retrieval-augmented generation; multi-role large language models; evidence-aware search; information retrieval; artificial intelligence governance; robustness; fairness; sustainabilityAbstract
Retrieval-augmented generation has become a central architecture for grounding large language models in external evidence, yet most deployed systems still treat retrieval, reranking, and generation as a linear pipeline rather than a contested socio-technical process. This paper examines retrieval-augmented generation with multi-role large language models for evidence-aware search, focusing on how specialized model roles can improve search quality while introducing new governance, robustness, fairness, and sustainability challenges. We synthesize research on dense retrieval, fusion-in-decoder architectures, retrieval-augmented pretraining, late interaction, benchmarking, self-reflection, tool use, planning, long-context handling, irrelevant context susceptibility, parametric memory limits, calibration, hallucination, and foundation model risks. We then analyze a multi-role architecture in which separate language model roles perform query interpretation, evidence retrieval, adversarial verification, synthesis, and audit. The paper argues that evidence-aware search should be understood as infrastructure: it requires versioned evidence stores, provenance metadata, role separation, observability, escalation paths, and policy controls that extend beyond model accuracy. Multi-role designs can improve precision, reduce hallucination, and support contestability, but they also increase latency, cost, energy use, and coordination failure modes. We conclude that sustainable deployment depends on matching role complexity to domain risk, investing in auditability and data governance, and treating retrieval corpora and ranking policies as public-interest infrastructure rather than opaque private assets.
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. 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.
3. 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: Main Volume (pp. 874–880). Association for Computational Linguistics.
4. 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 (pp. 2206–2240). PMLR.
5. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M.-W. (2020). REALM: Retrieval-augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning (pp. 3929–3938). PMLR.
6. Khattab, O., & Zaharia, M. (2020). ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 39–48). Association for Computing Machinery.
7. Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., & Gurevych, I. (2021). BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, 1.
8. 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 preprint arXiv:2312.10997.
9. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2023). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. arXiv preprint arXiv:2310.11511.
10. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. In Proceedings of the 11th International Conference on Learning Representations.
11. Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36.
12. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
13. Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., & Lim, E.-P. (2023). Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (pp. 2609–2634). Association for Computational Linguistics.
14. Jin, C., Peng, H., Zhang, A., Chen, N., Zhao, J., Xie, X., ... & Metaxas, D. N. (2025, May). Rankflow: A multi-role collaborative reranking workflow utilizing large language models. In Companion Proceedings of the ACM on Web Conference 2025 (pp. 2484-2493).
15. Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2023). Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12, 157–173.
16. Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E., Schärli, N., & Zhou, D. (2023). Large language models can be easily distracted by irrelevant context. In Proceedings of the 40th International Conference on Machine Learning (pp. 31210–31227). PMLR.
17. Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., & Hajishirzi, H. (2023). When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (pp. 9802–9822). Association for Computational Linguistics.
18. Kadavath, S., Conerly, T., Askell, A., Henighan, T., Drain, D., Perez, E., Schiefer, N., Dodds, Z. H., 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 preprint arXiv:2207.05221.
19. 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.
20. 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 preprint arXiv:2108.07258.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Artificial Intelligence and Machine Learning Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.