3 papers
cs.AI2026
Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL
Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
Large language models can generate fluent SQL from natural language, but on real enterprise Oracle databases they frequently fail at execution time: columns and aliases are halluci…
cs.CL2026
Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework
Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compo…
cs.SE2026
CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories
Divya Chukkapalli, Thejesh Avula, Aditya Aggarwal +2
Software repositories accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads, but developers and AI coding assistants ra…