Adversarial Robustness in Retrieval-Augmented Generation for Quranic Studies Across Open-Source LLM Scales and Architectural
Abstract
Abstract: Accurate and contextually faithful responses are critical when applying large language models (LLMs) to sensitive and domain-specific tasks, such as answering queries related to quranic studies. General-purpose LLMs often struggle with hallucinations, where generated responses deviate from authoritative sources, raising concerns about their reliability in religious contexts. This challenge highlights the need for systems that can integrate domain-specific knowledge while maintaining response accuracy, relevance, and faithfulness. In this study, we investigate 13 open-source LLMs categorized in
Research Question
How does adversarial robustness in retrieval-augmented generation (measured by accuracy drop under perturbed or misleading prompts) vary across different open-source LLMs (7B vs. 70B) when applied to domain-specific tasks like Quranic studies, and what architectural modifications (e.g., attention mechanisms) mitigate this?
Verification Level
| Paper level | L2, Source-grounded claims | |
| Source-grounded claims | 9 | |
| Claim record source | parsed source sections |
Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.
Truth-Engine Gate Verdict
| Status | Verified | |
| Gate | Gate 2 — Verification (formal proof or sandbox reproduction) | |
| Reason | Sealed-sandbox formula repro: Computed 13.0 matches expected 13.0 (tolerance=5.0%). | |
| Evaluated | 2026-06-12T14:00:14.704347+00:00 |
This record has passed Gate 2: a Lean4 proof source type-checks, or a sealed-sandbox run reproduced the reported results within the stated tolerance. A reproducible artifact (proof source or repro script and results) is attached to this record. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.
Quality Tier
| Tier | DOI grade | |
| Basis | Review score and verified-claim count meet DOI-grade public quality thresholds. |
Descriptive public triage only; this tier does not alter current publication or DOI behavior.
Quality Dimensions
| Evidence strength | MEDIUM | |
| Citation grounding | MEDIUM | |
| Uncertainty disclosure | MEDIUM | |
| Reproducibility status | HIGH |
Automated triage signals derived from public fields; not human peer review or independent validation.
Correction Record
| Status | CURRENT |
| Correction count | 0 |
| Manifest contract | paper-manifest-v1.1 |
| Correction contract | correction-record-v1 |
Public corrections are additive records. Current status does not claim the synthesis is error-free.
Provenance
| Publisher | Assignee Research |
| Public provenance | L4, External archival record |
| Report artifact | Available |
| External record | Registered |
| Claim lineage | 9 aggregate source-grounded claims |
| Review method | Automated multi-reviewer assessment |
| Quality guide | How to read scores, claims, manifests, and evidence links |
| Provenance contract | source-provenance-v1 |
| Note | Machine-generated synthesis of existing literature. Not primary research. |