Salvato in:
Dettagli Bibliografici
Autori principali: Doan, Bao Gia, Joshi, Aditya, Elinas, Pantelis, Bodhankar, Aarya, Leslie, Oscar, Marchant, Tom, Salim, Flora
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.17943
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911722437083136
author Doan, Bao Gia
Joshi, Aditya
Elinas, Pantelis
Bodhankar, Aarya
Leslie, Oscar
Marchant, Tom
Salim, Flora
author_facet Doan, Bao Gia
Joshi, Aditya
Elinas, Pantelis
Bodhankar, Aarya
Leslie, Oscar
Marchant, Tom
Salim, Flora
contents RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark construction and evaluation framework using only a small set of specialist domain documents. DoRA systematically generates synthetic QA training and evaluation datasets with auditable evidence across five domain-specific intents. To mitigate same-pipeline circularity, DoRA's training and test splits use different LLM families (Claude Sonnet for training; GPT-4o for test) drawn from disjoint seed-document corpora. Instantiated on 40 defense-related documents (written in English), DoRA yields ~6.6K curated instances. Compared against 8 LLM baselines over a benchmark of 1,259 samples, a LoRA-adapted Llama3.1-8B trained on the synthetic training set consistently improves performance over 6 coverage and faithfulness metrics, especially reducing hallucination by more than half under the default GTE retrieval setting, with gains persisting across alternative retrievers and prompting-based baselines. Defense-domain expertise is incorporated in three stages of our evaluation: (a) determining the quality of the synthetic QA generated by DoRA, (b) ascertaining the reliability of LLM-as-judge scores, and (c) evaluating the generalization of the QA pipeline on completely human-written QA examples. We position DoRA as a practical framework for specialist-domain RAG under domain shift, with defense as a high-stakes case study.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17943
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
Doan, Bao Gia
Joshi, Aditya
Elinas, Pantelis
Bodhankar, Aarya
Leslie, Oscar
Marchant, Tom
Salim, Flora
Computation and Language
RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark construction and evaluation framework using only a small set of specialist domain documents. DoRA systematically generates synthetic QA training and evaluation datasets with auditable evidence across five domain-specific intents. To mitigate same-pipeline circularity, DoRA's training and test splits use different LLM families (Claude Sonnet for training; GPT-4o for test) drawn from disjoint seed-document corpora. Instantiated on 40 defense-related documents (written in English), DoRA yields ~6.6K curated instances. Compared against 8 LLM baselines over a benchmark of 1,259 samples, a LoRA-adapted Llama3.1-8B trained on the synthetic training set consistently improves performance over 6 coverage and faithfulness metrics, especially reducing hallucination by more than half under the default GTE retrieval setting, with gains persisting across alternative retrievers and prompting-based baselines. Defense-domain expertise is incorporated in three stages of our evaluation: (a) determining the quality of the synthetic QA generated by DoRA, (b) ascertaining the reliability of LLM-as-judge scores, and (c) evaluating the generalization of the QA pipeline on completely human-written QA examples. We position DoRA as a practical framework for specialist-domain RAG under domain shift, with defense as a high-stakes case study.
title A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
topic Computation and Language
url https://arxiv.org/abs/2604.17943