Model Transparency Report

Comprehensive documentation of the AI systems powering Aevum Encyclopedia's knowledge retrieval, synthesis, and verification pipelines.

Model Identifier
Aevum-Knowledge-3.2
Publication Date
2024-11-15
Last Updated
2025-03-28
Report Version
v2.4.1

1. Executive Summary

This report outlines the architecture, training methodology, evaluation metrics, safety protocols, and governance framework for Aevum-Knowledge-3, the primary large language model (LLM) powering Aevum Encyclopedia's AI-assisted search, content synthesis, citation verification, and multilingual translation features.

Aevum Encyclopedia is committed to radical transparency regarding our AI systems. This document is intended for researchers, educators, compliance auditors, and the general public. All claims are supported by internal evaluations and third-party audits where applicable.

⚠️ Important Scope Note

This report covers the base knowledge model and its production fine-tunes. It does not cover third-party integrations or legacy rule-based systems still in maintenance mode.

2. Model Architecture & Capabilities

Aevum-Knowledge-3.2 is a sparse mixture-of-experts (MoE) transformer optimized for factual retrieval, long-context reasoning, and academic-grade synthesis.

Parameter Specification
ArchitectureDense + MoE Hybrid (32 Experts, 8 Activated)
Total Parameters137B (Active: 14.2B)
Context Window128K tokens
VocabularyCustom BPE + WordPiece (256K tokens)
Inference FrameworkvLLM + Custom KV-Cache Optimizer
Latency (P95)320ms (first token), 850ms (full response)
Supported ModalitiesText, Structured Data, Metadata Graphs

Core Capabilities

  • Cross-Document Synthesis: Aggregates verified claims across thousands of sources while preserving attribution.
  • Fact-Verification Pipeline: Real-time cross-referencing against a curated knowledge graph and primary source archive.
  • Multilingual Grounding: Native training across 140+ languages with culture-aware terminology mapping.
  • Academic Formatting: Automatic generation of APA, MLA, Chicago, and IEEE citation structures.

3. Training Data & Provenance

Training data was curated using a multi-stage filtering pipeline designed to prioritize academic rigor, copyright compliance, and demographic balance.

Data Sources & Composition

CategoryProportionExamplesLicensing
Open Academic & Preprints42%arXiv, PubMed, OpenAlex, DOAJCC-BY, Open Access
Encyclopedia & Reference28%Wikipedia, Britannica (licensed), Stanford EncyclopediaCC-BY-SA, Commercial
Gov & Institutional Reports18%UN, WHO, NOAA, OECD, National ArchivesPublic Domain
Curated Media & Journalism8%Reuters, AP, Associated Press ArchiveLicensed
Synthetic & Augmented4%Controlled QA pairs, citation exercisesProprietary

Preprocessing & Filtering

  • Deduplication: MinHash + LSH fingerprinting reduced exact/near-duplicate content by 34%.
  • Toxicity & Bias Screening: Multi-layer classifier removed content exceeding safety thresholds (F1: 0.94 on detoxified benchmarks).
  • PII Removal: NER-based redaction pipeline achieved 99.2% precision on personal identifiers.
  • Licensing Verification: Automated crawler + legal review board validated usage rights for all commercial datasets.

4. Evaluation & Benchmarks

The model undergoes continuous evaluation across factual accuracy, hallucination rates, bias metrics, and safety alignment.

BenchmarkScoreIndustry AvgStatus
MMLU (Academic)89.4%82.1%Above
TruthfulQA91.2%78.5%Above
FACTS-Citation Recall96.8%88.0%Above
Hallucination Rate (Open QA)2.1%6.4%Below
Cross-Cultural Bias (CC-Bias)0.180.34Monitored
📊 Third-Party Audit

Independent evaluation by AI Governance Institute (AIGI) completed Q2 2025. Full technical annex available upon request for accredited researchers.

5. Risk Assessment & Mitigations

We proactively identify and document systemic risks associated with model deployment in an educational and research context.

Identified Risks

Risk CategorySeverityMitigation Strategy
Factual HallucinationHighReal-time citation gating; refusal to answer unverified claims; confidence scoring
Cultural/Linguistic BiasMediumCurated multilingual fine-tuning; periodic bias audits; regional expert review panels
Academic MisuseMediumPlagiarism-aware output markers; institutional API watermarking; educational guidelines
Adversarial PromptingLowInput sanitization layer; rate limiting; behavior anomaly detection

Safety Filters

  • Pre-Processing: Prompt classification blocks harmful, deceptive, or overly broad queries.
  • In-Context: Confidence thresholds trigger fallback to reference sources or clarification requests.
  • Post-Processing: Output scanning flags unverified claims, missing citations, or tone inconsistencies before delivery.

6. Governance & Oversight

Aevum Encyclopedia maintains a multi-tiered governance structure to ensure responsible AI development and deployment.

Organizational Structure

  • AI Ethics Board: Independent panel of academics, legal experts, and civil society representatives.
  • Red-Team Unit: Internal group conducting monthly adversarial testing and edge-case discovery.
  • Community Review Panel: Volunteer subject-matter experts who flag discrepancies and suggest updates.

Compliance Standards

Our systems align with the EU AI Act (Category II: Limited Risk), NIST AI Risk Management Framework, and UNESCO Recommendation on the Ethics of AI. All model cards, data sheets, and impact assessments are version-controlled and publicly accessible.

7. Version History & Updates

VersionDateKey ChangesStatus
3.22025-03-10Enhanced citation verification; reduced hallucination rate by 14%; expanded Arabic/Indonesian supportCurrent
3.12024-11-20MoE architecture rollout; context window extended to 128K; academic formatting moduleLegacy
3.02024-06-15Base model release; 140-language support; initial safety filtersDeprecated

Major updates are preceded by 30-day public notice and compatibility testing. Deprecation cycles follow a 180-day sunset policy for enterprise APIs.

8. Contact & Feedback

We encourage researchers, educators, and users to submit feedback, report discrepancies, or request additional transparency documentation.

ChannelPurposeResponse Time
transparency@aevumencyclopedia.comGeneral inquiries, documentation requests3-5 business days
responsible-ai@aevumencyclopedia.comSafety concerns, bias reports, ethical feedback48 hours
Research Portal (aevum.dev/research)Benchmark datasets, model cards, technical annexesSelf-service
📝 Acknowledgment Process

All verified reports are logged in our internal incident tracker. Publicly actionable findings are documented in monthly transparency digest updates.