Rajdeep Mondal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Rajdeep Mondal has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Alan Tang
Microsoft, Redmond, WA, USA
2 shared publications - George Varghese
UCLA, Los Angeles, CA, USA
2 shared publications - Todd Millstein
University of California, Los Angeles, USA
2 shared publications - Nikolaj Bjørner
Microsoft, Redmond, WA, USA
1 shared publication - Ryan Beckett
Microsoft Research, Redmond, USA
1 shared publication
Latest Publications
- Open Access
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 176-183
Tackling Ambiguity in User Intent for LLM-based Network Configuration Synthesis
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 176-183
Open AccessTackling Ambiguity in User Intent for LLM-based Network Configuration Synthesis
- Top Cited PapersOpen Access
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 189-195
What do LLMs need to Synthesize Correct Router Configurations?
We investigate whether Large Language Models (e.g., GPT-4) can synthesize correct router configurations with reduced manual effort. We find GPT-4 works very badly by itself, producing promising draft configurations but with egregious errors in topology, syntax, and semantics. Our strategy, that we call Verified Prompt Programming, is to combine GPT-4 with verifiers, and use localized feedback from the verifier to automatically correct errors. Verification requires a specification and actionable localized feedback to be effective. We show results for two use cases: translating from Cisco to Juniper configurations on a single router, and implementing a no-transit policy on multiple routers. While human input is still required, if we define the leverage as the number of automated prompts to the number of human prompts, our experiments show a leverage of 10X for Juniper translation, and 6X for implementing the no-transit policy, ending with verified configurations.
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 189-195
Top Cited PapersOpen AccessWhat do LLMs need to Synthesize Correct Router Configurations?
We investigate whether Large Language Models (e.g., GPT-4) can synthesize correct router configurations with reduced manual effort. We find GPT-4 works very badly by itself, producing promising draft configurations but with egregious errors in topology, syntax, and semantics. Our strategy, that we call Verified Prompt Programming, is to combine GPT-4 with verifiers, and use localized feedback from the verifier to automatically correct errors. Verification requires a specification and actionable localized feedback to be effective. We show results for two use cases: translating from Cisco to Juniper configurations on a single router, and implementing a no-transit policy on multiple routers. While human input is still required, if we define the leverage as the number of automated prompts to the number of human prompts, our experiments show a leverage of 10X for Juniper translation, and 6X for implementing the no-transit policy, ending with verified configurations.