The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Establishing Trust for Using Natural Language for Intent-Based Networking
Open accessAbstract
Todays enterprise networks wrestle with accommodating an ever-growing number of devices of different types, supporting increasingly demanding applications and ever more complex services, and protecting their users from sophisticated and disrupting cyber threats. In response, a proposed architectural approach for improving network management, referred to as Intent-Based Networking (IBN), has attracted significant attention. It is built on the premise that network operators specify network policies in natural language and the network correctly translates these spoken intents (e.g., policies) into proper device-specific configurations that are then deployed across the network to reliably act on the operators expressed intents. Unfortunately, IBN has not yet fully delivered on its promise of automated, fast, and reliable policy deployment, mainly due to the significant challenges that the reliance on methods from Natural Language Processing (NLP) or more recent techniques from Machine Learning (ML) and Artificial Intelligence (AI) poses for unambiguously and accurately translating the myriad of intents that operators can express in natural language into “trustworthy” device configurations. This paper uses LUMI, a recently designed end-to-end prototype of a system that allows operators “to manage their network by talking to the network”, as an illustrative case study. In particular, we use it to elaborate on the different functionalities such systems should have to realize IBNs vision of automating the fast deployment of policies. At the same time, we leverage LUMI to highlight the extra efforts that are required to ensure that the deployed policies can be entrusted to accurately express and execute the operators original intents.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“pretraining contamination can silently inflate benchmark performance, and contamination checks are now part of mainstream LLM evaluation practice [147], [44], [139].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [44]
In the citing paper
“SWE-bench gives a related warning: evaluation changes when tasks involve real artefacts under constraints, rather than isolated question answering [44], [167].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [44]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Since the initial design of L UMI , new advances with Transformer recurrent neural networks [41] have led to improvements for solving the NER task [42] with models such as BERT [43], DIET [44] and GPT-4 [45].”
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 1×
“Since the initial design of L UMI , new advances with Transformer recurrent neural networks [41] have led to improvements for solving the NER task [42] with models such as BERT [43], DIET [44] and GPT-4 [45].”
WordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015 · cited 1×
“Since operators are free to refer to operation targets ( e.g., service, location, or type of traffic) using different words, L UMI relies on WordNet [53] to obtain synonyms of operation targets in both intents and also uses a dictionary of known “handles” for network devices and groups ( i.e.,…”
Named Entity Recognition with Bidirectional LSTM-CNNs
Chiu, J. P. C., & Nichols, E. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00104 · Cited by 1,909 · cited 1×
“L UMI ’ S NER architecture is described in detail in [14] and uses an enhanced version of the Long Short-Term Memory (LSTM) model ( i.e., the so-called Bi-LSTM model [39]).”
A Survey on Deep Learning for Named Entity Recognition
Li, J., Sun, A., Han, J., & Li, C. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2981314 · Cited by 1,567 · cited 1×
“Since the initial design of L UMI , new advances with Transformer recurrent neural networks [41] have led to improvements for solving the NER task [42] with models such as BERT [43], DIET [44] and GPT-4 [45].”
A survey on intent-based networking
Leivadeas, A., & Falkner, M. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3215919 · Cited by 326 · cited 1×
“Recent survey papers, such as [15], [16], summarize the latest efforts to realize the IBN vision for different networking domains, including enterprise and cellular networks.”
Sonata: query-driven streaming network telemetry
Gupta, A., Harrison, R., Canini, M., Feamster, N., Rexford, J., & Willinger, W. (2018) · Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication · doi:10.1145/3230543.3230555 · Cited by 273 · cited 1×
“However, deciding which traffic, devices, and properties to monitor and which data to collect will require instrumenting networks with an unprecedented level of control that is only possible by leveraging emerging programmable data plane technologies [59], [60].”
Self-citationPINT: Probabilistic In-band Network Telemetry
Ben Basat, R., Ramanathan, S., Li, Y., Antichi, G., Yu, M., & Mitzenmacher, M. (2020) · Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication · doi:10.1145/3387514.3405894 · Cited by 268 · cited 1×
“However, deciding which traffic, devices, and properties to monitor and which data to collect will require instrumenting networks with an unprecedented level of control that is only possible by leveraging emerging programmable data plane technologies [59], [60].”
A general approach to network configuration verification
Beckett, R., Gupta, A., Mahajan, R., & Walker, D. (2017) · Proceedings of the Conference of the ACM Special Interest Group on Data Communication · doi:10.1145/3098822.3098834 · Cited by 262 · cited 3×
“…quotas, QoS parameters, or high-level ACL rules, L UMI is prone to result in potentially conflicting intents that are outside the purview of commonly considered conflicts in the data plane [50] or control plane [1], [51] ( e.g., opposing forwarding behavior in distinct switches and routers).”
DIET: Lightweight Language Understanding for Dialogue SystemsPreprint
Bunk, T., Varshneya, D., Vlasov, V., & Nichol, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.09936 · Cited by 246 · cited 1×
“Since the initial design of L UMI , new advances with Transformer recurrent neural networks [41] have led to improvements for solving the NER task [42] with models such as BERT [43], DIET [44] and GPT-4 [45].”
Research works printed but not linked: 21
- Apostolopoulos, 2020, Improving networks with artificial intelligence
- Clemm, 2019, Intent-based networking—Concepts and definitions
- Narcisi, 2020, Juniper networks CEO: ‘The goal now is a self-driving network
- Liu, 2021, The practice of network verification in Alibaba’s global WAN
- Koley, The zero touch network
- Birkner, Net2Text: Query-guided summarization of network forwarding behaviors, 609
- Jacobs, Hey, Lumi! Using natural language for intent-based network management, 625
- Jurafsky, 2019, Speech and Language Processing
- Lafferty, Conditional random fields: Probabilistic models for segmenting and labeling sequence data, 282
- Achiam, 2023, Gpt-4 technical report
- 2024, Lumi supplemental material
- Kim, Kinetic: Verifiable dynamic network control, 59
- Khurshid, VeriFlow: Verifying network-wide invariants in real time, 15
- Fogel, A general approach to network configuration analysis, 469
- Marneffe, Finding contradictions in text, 1039
- Honnibal, 2017, SpaCy 2: Natural language understanding with bloom embeddings, convolutional neural networks, and incremental parsing
- Abhashkumar, Tiramisu: Fast and general network verification, 201
- Prabhu, Plankton: Scalable network configuration verification through model checking, 953
- Brownlee, 2020, Datasets for natural language processing
- 2011, Alphabetical List of free/public domain datasets with text data for use in natural language processing (NLP)
- 2022, Chatito: Generate datasets for AI Chatbots, NLP tasks, named entity recognition or text classification models using a simple DSL!
Cited by
Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety
Bilal, M., Crowcroft, J., Wang, R., Xu, X., & Dustdar, S. (2027) · Computer Science Review · doi:10.1016/j.cosrev.2026.101075 · Cited by 10
Intent-based System Design and Operation
Anand, V., Li, Y., Kumbhare, A. G., Irvene, C., Bansal, C., Somashekar, G., Mace, J., Las-Casas, P., Bianchini, R., & Fonseca, R. (2025) · Workshop on Practical Adoption Challenges of ML for Systems (PACMI) · doi:10.1145/3766882.3767182 · Cited by 4
Balaji, S., V, S, L. A., Manupati, R., & Kannan, B. (2026) · International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI) · doi:10.1109/raeeucci67649.2026.11504654
“The intents are normally in the natural language [7].”
Zou, Y., & Zou, S. (2026) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc69287.2026.11580103
“Early IBN implementations commonly adopt structured intent models and schema driven parsers, enabling deterministic compilation and easier validation [6].”
Aggressive-YoYo: Exploiting Intent-Semantic Misalignment in AI-Native 6G Management Planes
Chakraborty, N., Djukic, P., & Kantarcı, B. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3736983
“Existing studies have investigated malicious or ambiguous intents [16], Kubernetes autoscaling attacks [18], [20], and orchestration misconfigurations as largely separate problems.”
Metadata
- Authors
- Jacobs, A. S., Pfitscher, R. J., Ribeiro, R. H., Granville, L. Z., Ferreira, R. A., Willinger, W., & Rao, S. G.
- Affiliations
- Universidade Federal do Rio Grande do Sul (BR)
- Universidade Federal de Santa Catarina (BR)
- Universidade Federal de Mato Grosso do Sul (BR)
- NIKSUN Inc., Princeton, NJ, USA
- Purdue University West Lafayette (US)
- ORCID
- Venue
- IEEE Transactions on Network and Service Management
- Published
- 2025-10
- Volume
- 22
- Issue
- 5
- Pages
- 4775-4787
- ISSN
- 1932-4537 (ISSN-L)
- 2373-7379
- OpenAlex
- W4411086569
- Cited by
- 5
- References
- 37
- Citations by year
- 2026: 4 · 2025: 1
- FWCI
- 2.10
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Transactions on Network and Service Management (publishedVersion, cc-by)
- Funders
- Brazilian National Council for Scientific and Technological Development (CNPq) Procs (420934/2023-5, 308101/2022-7, 465446/2014-0, 142089/2018-4)
- Brazilian Coordination for the Improvement of Higher Education (CAPES) Finance Code 001; Sao Paulo Research Foundation (FAPESP) Procs (2020/05183-0, 2023/00811-0, 2023/00812-7)
- National Science Foundation (2319425)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Computer Networks and Communications › Mobile Agent-Based Network Management
- Physical Sciences › Computer Science › Computer Networks and Communications › Access Control and Trust
- Keywords
- intent-based networking, LUMI, network management automation, enterprise network management
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Establishing Trust for Using Natural Language for Intent-Based Networking. https://app.cochat.ai/papers/10.1109/tnsm.2025.3574626
- The paper
- Jacobs, A. S., Pfitscher, R. J., Ribeiro, R. H., Granville, L. Z., Ferreira, R. A., Willinger, W., & Rao, S. G. (2025). Establishing Trust for Using Natural Language for Intent-Based Networking. IEEE Transactions on Network and Service Management. https://doi.org/10.1109/tnsm.2025.3574626
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.