Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cook, Thomas, Patel, Kelly, Vellaichamy, Sivapriya, Sehwag, Udari Madhushani, Rahimi, Saba, Zeng, Zhen, Ganesh, Sumitra
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909930256072704
author Cook, Thomas
Patel, Kelly
Vellaichamy, Sivapriya
Sehwag, Udari Madhushani
Rahimi, Saba
Zeng, Zhen
Ganesh, Sumitra
author_facet Cook, Thomas
Patel, Kelly
Vellaichamy, Sivapriya
Sehwag, Udari Madhushani
Rahimi, Saba
Zeng, Zhen
Ganesh, Sumitra
contents Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in text-to-SQL, where a learning agent receives natural language feedback to refine queries and distills the revealed knowledge for reuse on future tasks. This distilled knowledge is stored in a structured memory, enabling the agent to improve execution accuracy over time. We design and evaluate multiple variations of a learning agent architecture that vary in how they capture and retrieve past experiences. Experiments on the BIRD benchmark Dev set show that memory-augmented agents, particularly the Procedural Agent, achieve significant accuracy gains and error reduction by leveraging human-in-the-loop feedback. Our results highlight the importance of transforming tacit human expertise into reusable knowledge, paving the way for more adaptive, domain-aware text-to-SQL systems that continually learn from a human-in-the-loop.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10674
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL
Cook, Thomas
Patel, Kelly
Vellaichamy, Sivapriya
Sehwag, Udari Madhushani
Rahimi, Saba
Zeng, Zhen
Ganesh, Sumitra
Computation and Language
Artificial Intelligence
Databases
68T05
Large Language Models (LLMs) can generate SQL queries from natural language questions but struggle with database-specific schemas and tacit domain knowledge. We introduce a framework for continual learning from human feedback in text-to-SQL, where a learning agent receives natural language feedback to refine queries and distills the revealed knowledge for reuse on future tasks. This distilled knowledge is stored in a structured memory, enabling the agent to improve execution accuracy over time. We design and evaluate multiple variations of a learning agent architecture that vary in how they capture and retrieve past experiences. Experiments on the BIRD benchmark Dev set show that memory-augmented agents, particularly the Procedural Agent, achieve significant accuracy gains and error reduction by leveraging human-in-the-loop feedback. Our results highlight the importance of transforming tacit human expertise into reusable knowledge, paving the way for more adaptive, domain-aware text-to-SQL systems that continually learn from a human-in-the-loop.
title Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL
topic Computation and Language
Artificial Intelligence
Databases
68T05
url https://arxiv.org/abs/2511.10674