AI-Powered Decision Support for Modern Enterprises
DOI:
https://doi.org/10.5281/zenodo.20591773Keywords:
Context-Preserving Generative AI,Enterprise Knowledge Workflows,LLM-RAG Framework,Retrieval-Augmented Generation (RAG),Real-Time Decision Support,Management Decision Intelligence,Enterprise Knowledge Management (EKM),Semantic Search,Hybrid Retrieval (Sparse + Dense),Contextual Grounding,Policy-Aware Generation,Role-Based Access Control (RBAC),Data Governance & Compliance,Human-in-the-Loop (HITL),Explainability & Provenance Tracking.Abstract
Enterprises generate large volumes of unstructured information in reports, presentations, and conversations. This information often resides in diverse, distributed data sources, limiting its use for direct decision-making and leading to the adoption of adhoc workflows. The delay, inaccuracy, and poor governance of such work increase risk. A variety of solutions have sought to improve the integration of knowledge work into enterprise processes.
A Retrieval-Augmented Generation framework, augmented with a context-preserving knowledge-retrieval layer, provides decision-support capabilities across preset operation, logistics, planning, and compliance domains. Tools, interfaces, and monitoring dashboards allow for real-time context creation, approval, and rollback during LLM inference. Data provenance tracks root sources, promotes trust in responses, and accelerates compliance audits.
References
[1] Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., 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., 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 (EMNLP), 6769–6781.
[3] Izacard, G., Caron, M., Hosseini, L., Riedel, S., Bojanowski, P., Joulin, A., & Grave, E. (2022). Unsupervised dense information retrieval with contrastive learning. Transactions of the Association for Computational Linguistics, 10, 1507–1524.
[4] Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv.
[5] Fan, W., Ding, Y., Ning, Z., Liang, S., Wang, S., Li, H., Yin, D., & Tang, J. (2024). A survey on RAG meeting LLMs: Towards retrieval-augmented large language models. Proceedings of the ACM on Management of Data, 2(2), 1–28.
[6] Gupta, S., Sharma, A., Singh, S., & Agarwal, A. (2024). A comprehensive survey of retrieval-augmented generation (RAG): Evolution, architectures, and applications. arXiv.
[7] Asai, A., Wu, Z., Wang, Y., Hajishirzi, H., & Yih, W.-T. (2023). Self-RAG: Learning to retrieve, generate, and critique through self-reflection. arXiv.
[8] Luo, M., Zhang, Y., Zhu, Z., Chen, D., & Li, J. (2023). RARR: Researching and revising answers with retrieval. arXiv.
[9] Shuster, K., Piktus, A., Petroni, F., Kiela, D., Lewis, P., & Weston, J. (2021). Retrieval augmentation reduces hallucination in conversation. arXiv.
[10] Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Sutawika, L., & others. (2023). Augmented language models: A survey. arXiv.
[11] Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., Gao, J., Liu, J., & Dolan, B. (2020). DialogPT: Large-scale generative pre-training for conversational response generation. Proceedings of ACL 2020: System Demonstrations, 270–278.
[12] Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Rozière, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023). LLaMA: Open and efficient foundation language models. arXiv.
[13] Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., others. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv.
[14] Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., others. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744.
[15] Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., & others. (2022). Constitutional AI: Harmlessness from AI feedback. arXiv.
[16] Ziegler, D. M., Stiennon, N., Wu, J., Brown, T., Radford, A., Amodei, D., Christiano, P. F., & Irving, G. (2019). Fine-tuning language models from human preferences. arXiv.
[17] Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Stoica, I., & others. (2023). Efficient memory management for large language model serving with PagedAttention. Proceedings of the 29th ACM Symposium on Operating Systems Principles, 735–750.
[18] Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. Proceedings of ACL-IJCNLP 2021, 4582–4597.
[[19] 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 (ICLR).
[20] Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. Proceedings of EMNLP 2021, 3045–3059.
[21] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
[22] Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., others. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
[23] Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
[24] Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations (ICLR).
[25] Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199–22213.
[26] Nair, V., Schumacher, E., Tiwary, R., Singh, A., Zhang, Y., & others. (2023). Datasets and evaluation for retrieval augmented generation: A survey. arXiv.
[27] Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J.-B., Damoc, B., Clark, A., others. (2022). Improving language models by retrieving from trillions of tokens. International Conference on Machine Learning (ICML), 2206–2240.
[28] Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M.-W. (2020). REALM: Retrieval-augmented language model pre-training. Proceedings of ICML 2020, 3929–3938.
[29] Khattab, O., & Zaharia, M. (2020). ColBERT: Efficient and effective passage search via contextualized late interaction over BERT. Proceedings of SIGIR 2020, 39–48.
[30] Wang, L., Zhang, Y., & others. (2023). RAG-based enterprise question answering: Architectures, evaluation, and deployment lessons. arXiv.
[31] Zhu, Z., Luo, M., Li, J., & Chen, D. (2024). Evaluating citation grounding and factual consistency in retrieval-augmented generation. arXiv.
[32] United States National Institute of Standards and Technology. (2023). Artificial intelligence risk management framework (AI RMF 1.0) (NIST AI 100-1). National Institute of Standards and Technology.
[33] European Parliament and Council of the European Union. (2024). Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). Official Journal of the European Union.
[34] Shah, N., Jain, S., & others. (2024). Secure retrieval-augmented generation for enterprise knowledge: Access control, redaction, and auditability. arXiv.
[35] Chen, L., Zaharia, M., & Zou, J. (2023). How is ChatGPT’s behavior changing over time? arXiv.
[36] Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020). On faithfulness and factuality in abstractive summarization. Proceedings of ACL 2020, 1906–1919.
[37] 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.
[38] Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., & others. (2022). OPT: Open pre-trained transformer language models. arXiv.
[39] Hope, T., Portenoy, J., Vasan, K., Borchardt, J., Horvitz, E., Weld, D. S., & others. (2022). SciFact: A benchmark for scientific claim verification. Proceedings of AAAI 2022, 12301–12308.
Additional Files
Published
Data Availability Statement
NONE
