# K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling

arXiv: https://arxiv.org/abs/2509.16929 · HTML: https://mlsanity.com/paper/2509.16929/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 33)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Orthogonal Subspace Learning for Language Model Continual Learning](https://mlsanity.com/paper/2310.14152/) (2023)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2210.00063/) (2022)
- [Few-shot In-context Learning for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.01750/) (2023)
- [Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning](https://mlsanity.com/paper/2311.11077/) (2023)
- [A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges](https://mlsanity.com/paper/2204.04859/) (2022)
- [SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models](https://mlsanity.com/paper/2401.08295/) (2024)
- [FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis](https://mlsanity.com/paper/2401.10506/) (2024)
- [Semantic Residual Prompts for Continual Learning](https://mlsanity.com/paper/2403.06870/) (2024)
- [Improving Semantic Parsing for Task Oriented Dialog](https://mlsanity.com/paper/1902.06000/) (2019)
- [Code-Style In-Context Learning for Knowledge-Based Question Answering](https://mlsanity.com/paper/2309.04695/) (2023)
- [Large Knowledge Model: Perspectives and Challenges](https://mlsanity.com/paper/2312.02706/) (2023)
- [Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams](https://mlsanity.com/paper/2211.11226/) (2022)

## Built on by (most cited first, 2 of 2)

- [StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models](https://mlsanity.com/paper/2605.01939/) (2026)
- [Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation](https://mlsanity.com/paper/2603.05873/) (2026)

## Abstract (arXiv)

Continual Structured Knowledge Reasoning (CSKR) focuses on training models to handle sequential tasks, where each task involves translating natural language questions into structured queries grounded in structured knowledge. Existing general continual learning approaches face significant challenges when applied to this task, including poor generalization to heterogeneous structured knowledge and inefficient reasoning due to parameter growth as tasks increase. To address these limitations, we propose a novel CSKR framework, textscK-DeCore, which operates with a fixed number of tunable parameters. Unlike prior methods, textscK-DeCore introduces a knowledge decoupling mechanism that disentangles the reasoning process into task-specific and task-agnostic stages, effectively bridging the gaps across diverse tasks. Building on this foundation, textscK-DeCore integrates a dual-perspective memory consolidation mechanism for distinct stages and introduces a structure-guided pseudo-data synthesis strategy to further enhance the model's generalization capabilities. Extensive experiments on four benchmark datasets demonstrate the superiority of textscK-DeCore over existing continual learning methods across multiple metrics, leveraging various backbone large language models.