# DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models

arXiv: https://arxiv.org/abs/2609.02685 · HTML: https://mlsanity.com/paper/2609.02685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning](https://mlsanity.com/paper/2310.16049/) (2023)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs](https://mlsanity.com/paper/2404.13081/) (2024)
- [Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages](https://mlsanity.com/paper/2310.04799/) (2023)
- [Improving Retrieval for RAG based Question Answering Models on Financial Documents](https://mlsanity.com/paper/2404.07221/) (2024)
- [ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning](https://mlsanity.com/paper/2501.06590/) (2025)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Demystifying Domain-adaptive Post-training for Financial LLMs](https://mlsanity.com/paper/2501.04961/) (2025)
- [PLLaMa: An Open-source Large Language Model for Plant Science](https://mlsanity.com/paper/2401.01600/) (2024)
- [Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions](https://mlsanity.com/paper/2504.05571/) (2025)

## Built on by (most cited first, 1 of 1)

- [ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI](https://mlsanity.com/paper/2609.22285/) (2026)

## Abstract (arXiv)

RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when retrieval is incorrect or incomplete, leading to hallucinations. Finetuning methods such as RAFT and PA-RAG enhance RAG by injecting new knowledge into the model's parameters, but require generating a massive amount of synthetic QA that covers the entire corpus. Extended Pre-Training (EPT) on the text corpus avoids the need for comprehensive synthetic data generation but compromises an Instruct LLM's instruction-following capabilities, necessitating instruction fine-tuning (IFT) after pre-training. However, IFT is costly and may be infeasible due to the unavailability of an instruction-tuning corpus. In this work, we propose DKL-Decoupled Knowledge Learning for Instruction-Tuned Language Models. Instead of doing EPT on the Instruct LLM, DKL performs EPT on its corresponding base LLM to infuse new knowledge. These knowledge infused weights are then merged with the Instruct LLM, imparting new knowledge without affecting their instruction-following capabilities. DKL is a lightweight method that avoids expensive instruction fine-tuning and relies on model merging to infuse the new knowledge into the Instruct LLM without destroying its instruction following capabilities. Empirical results show that DKL improves RAG accuracy from 54.17 to 79.26 on retrieval failure cases, while outperforming prior approaches with substantially less training data.