SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

• URL: http://arxiv.org/abs/2509.10708v1
• Date: Fri, 12 Sep 2025 21:50:39 GMT
• Title: SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation
• Authors: Iman Barati, Mostafa Amiri, Heshaam Faili,
• Abstract summary: Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs)<n>We propose SearchInstruct, a method explicitly designed to construct high quality instruction datasets for SFT.<n>Our approach begins with a limited set of domain specific, human generated questions, which are systematically expanded using a large language model.
• Score: 3.5939555573102857
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs), significantly enhancing critical capabilities such as instruction following and in-context learning. Nevertheless, creating suitable training datasets tailored for specific domains remains challenging due to unique domain constraints and data scarcity. In this paper, we propose SearchInstruct, an innovative method explicitly designed to construct high quality instruction datasets for SFT. Our approach begins with a limited set of domain specific, human generated questions, which are systematically expanded using a large language model. Subsequently, domain relevant resources are dynamically retrieved to generate accurate and contextually appropriate answers for each augmented question. Experimental evaluation demonstrates that SearchInstruct enhances both the diversity and quality of SFT datasets, leading to measurable improvements in LLM performance within specialized domains. Additionally, we show that beyond dataset generation, the proposed method can also effectively facilitate tasks such as model editing, enabling efficient updates to existing models. To facilitate reproducibility and community adoption, we provide full implementation details, the complete set of generated instruction response pairs, and the source code in a publicly accessible Git repository: [https://github.com/mostafaamiri/SearchInstruct](https://github.com/mostafaamiri/SearchInstruct)

Related papers

• Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation [18.99847259801634]
  We propose Reinforcement Learning from Augmented Generation (RLAG) to embed domain knowledge into large language models.<n>Our approach iteratively cycles between sampling generations and optimize the model through calculated rewards.<n> Experimental results across medical, legal, astronomy, and current events datasets demonstrate that our proposed method significantly outperforms baseline approaches.
  arXiv  Detail & Related papers  (2025-09-24T14:30:16Z)
• LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding [55.5535016040221]
  LM-Searcher is a novel framework for cross-domain neural architecture optimization.<n>Central to our approach is NCode, a universal numerical string representation for neural architectures.<n>Our dataset, encompassing a wide range of architecture-performance pairs, encourages robust and transferable learning.
  arXiv  Detail & Related papers  (2025-09-06T09:26:39Z)
• Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization [15.402666674186937]
  We leverage parameter-efficient fine-tuning techniques (PEFTs) on high-resource datasets to improve performance on unseen low-resource domains.<n>We benchmark six PEFTs with textttLlama-3-8B-Instruct on 14 training datasets from the Scientific, Medical, Legal, and News domains.<n>Experiments show that for low-resource domains, inference using Within-Domain Adapters can achieve better performance than Few-Shot.
  arXiv  Detail & Related papers  (2025-09-01T09:58:52Z)
• Scaling Towards the Information Boundary of Instruction Set: InfinityInstruct-Subject Technical Report [11.70656700216213]
  Construction of high-quality instruction datasets is crucial for enhancing model performance and generalizability.<n>We propose a systematic instruction data synthesis framework, which integrates a hierarchical labeling system, an informative seed selection algorithm, and a model deficiency diagnosis.<n>Based on this framework, we construct InfinityInstruct-Subject, a high-quality dataset containing 1.5 million instructions.
  arXiv  Detail & Related papers  (2025-07-09T15:59:02Z)
• Towards Efficient and Effective Alignment of Large Language Models [7.853945494882636]
  Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge.<n>This thesis advances LLM alignment by introducing novel methodologies in data collection, training, and evaluation.
  arXiv  Detail & Related papers  (2025-06-11T02:08:52Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• RedStone: Curating General, Code, Math, and QA Data for Large Language Models [134.49774529790693]
  This study explores the untapped potential of Common Crawl as a comprehensive and flexible resource for pre-training Large Language Models.<n>We introduce RedStone, an innovative and scalable pipeline engineered to extract and process data from Common Crawl.
  arXiv  Detail & Related papers  (2024-12-04T15:27:39Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning [0.0]
  This research proposes a pipeline to construct high-quality instruction datasets for fine-tuning on specific domains. By ingesting domain-specific documents, the pipeline generates relevant and contextually appropriate instructions. As a case study, we apply this approach to the domain of psychiatry, a field requiring specialized knowledge and sensitive handling of patient information.
  arXiv  Detail & Related papers  (2024-08-12T03:52:11Z)
• Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases [9.478012553728538]
  We propose an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Our experiments demonstrate the system's effectiveness in generating more accurate answers to domain-specific and time-sensitive inquiries.
  arXiv  Detail & Related papers  (2024-03-15T16:30:14Z)
• Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration [64.58185031596169]
  Explore-Instruct is a novel approach to enhance the data coverage to be used in domain-specific instruction-tuning. Our data-centric analysis validates the effectiveness of this proposed approach in improving domain-specific instruction coverage. Our findings offer a promising opportunity to improve instruction coverage, especially in domain-specific contexts.
  arXiv  Detail & Related papers  (2023-10-13T15:03:15Z)
• Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation [92.2167864437497]
  We propose Dynosaur, a dynamic growth paradigm for the automatic curation of instruction-tuning data. Based on the metadata of existing datasets, we use LLMs to automatically construct instruction-tuning data by identifying relevant data fields and generating appropriate instructions. By leveraging the existing annotated datasets, Dynosaur offers several advantages: 1) it reduces the API cost for generating instructions; 2) it provides high-quality data for instruction tuning; and 3) it supports the continuous improvement of models by generating instruction-tuning data when a new annotated dataset becomes available.
  arXiv  Detail & Related papers  (2023-05-23T17:56:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.