Sitemap
All pages on this site
Pages
Blog
- Bilingual Belgian tax law: why NL/FR is a prerequisite, not a feature Mar 2026
- Harvey, Blue J, Legora: what we can learn from the big players in legal AI Mar 2026
- AI adoption in legal professions: where we stand in 2026 Mar 2026
- Why Belgium is the perfect market for specialized tax AI Mar 2026
- How we handle contradictory sources — and why most AI tools don't Mar 2026
- Why we publish our accuracy — and why almost nobody else does Mar 2026
- AI and professional liability: what happens when the answer is wrong? Mar 2026
- Behind the scenes: how a law change flows through a legal AI system Mar 2026
- What the Stanford hallucination study actually revealed — and why the industry's response missed the point Mar 2026
- What is reranking — and why it's the difference between finding documents and finding answers Mar 2026
- How hybrid search works — and why your legal AI tool probably uses only half the equation Feb 2026
- Implementing AI in your tax practice: why trust matters more than technology Feb 2026
- Case study: estate planning across three regions — one family, three tax outcomes Feb 2026
- The EU AI Act and legal AI: what Belgian tax professionals actually need to know Feb 2026
- The future of tax research: what AI changes, what it doesn't, and what that means for your practice Feb 2026
- What is a knowledge graph — and why it changes how AI navigates Belgian tax law Feb 2026
- What is chunking — and why it's the invisible foundation of legal AI quality Feb 2026
- How much time does tax AI actually save? An honest estimate Feb 2026
- Three regions, three tax systems: why Belgian fiscal advice requires side-by-side comparison Feb 2026
- What is temporal versioning — and why your legal AI tool probably serves you yesterday's law Feb 2026
- Case study: TAK 23 — why one product needs five tax answers Feb 2026
- Why we're not building a chatbot Feb 2026
- What is authority ranking — and why your legal AI tool probably ignores it Feb 2026
- 5 Belgian tax questions where generic AI is guaranteed to fail Feb 2026
- "I don't trust AI for tax advice" — and you're right. Here's why you should try it anyway. Feb 2026
- What is confidence scoring — and why it's more honest than a confident answer Feb 2026
- Fine-tuning vs. RAG: two ways to make AI smart — and why it matters which one your tax tool chose Feb 2026
- How to evaluate a legal AI tool: 10 questions that actually matter Feb 2026
- Why transparency matters more than accuracy in legal AI Feb 2026
- What is RAG — and why it's not enough for legal AI on its own Feb 2026
- AI hallucinations: why ChatGPT fabricates sources (and how to spot it) Feb 2026
- I asked ChatGPT and Auryth the same Belgian tax questions — here's what happened Feb 2026
Glossary
- Access control
- Adapter
- Adversarial testing
- AI Conformity Assessment
- AI Documentation Requirements
- AI Governance Framework
- AI Risk Management
- Algorithmic Transparency
- Alignment
- Answer grounding
- Approximate Nearest Neighbor
- Attention Mechanism
- Attribution
- Audit trail
- Authority Ranking Model
- Backpropagation
- Beam Search
- Benchmarking
- Bi-Encoder
- Bias Mitigation
- BM25
- Boolean Search
- Byte Pair Encoding (BPE)
- Calibration
- Chain-of-Thought
- Chunking Strategy
- Citation
- Compliance-Aware Retrieval
- Confidence interval
- Confidence scoring
- Content Discoverability
- Content indexing
- Context injection
- Context Window
- Continuous evaluation
- Corpus
- Cosine Similarity
- Cross-Encoder
- Data Ethics
- Data governance
- Data pipeline
- Data preprocessing
- Data residency
- Data retention policy
- Deduplication
- Deep Learning
- Dense Retrieval
- Dimensionality reduction
- Distance metric
- Document chunk
- Document ingestion
- Document normalization
- Document parsing
- Dot product similarity
- Embedding alignment
- Embedding compression
- Embedding drift
- Embedding model
- Embedding space
- Embeddings
- Entity extraction
- Error analysis
- EU AI Act
- Euclidean distance
- Evals framework
- Evaluation dataset
- Explainability
- Factual consistency
- Factuality
- FAISS
- Faithfulness
- Feed-forward network
- Few-Shot Learning
- Fine-Tuning
- Full-Text Search
- Function calling
- Generative layer
- Gradient Descent
- Greedy Decoding
- Ground Truth
- Grounding
- Guardrails
- Hallucination
- Hallucination rate
- High-Risk AI System
- HNSW
- Human Oversight
- Human-in-the-loop validation
- Hybrid indexing
- Hybrid Search
- In-Context Learning
- Index refresh
- Index sharding
- Indexing Strategy
- Inference
- Information retrieval system
- Instruction Tuning
- Inverted Index
- Iterative retrieval
- Jailbreaking
- Knowledge base
- Knowledge Distillation
- Knowledge Graph
- Knowledge retrieval strategy
- Legal Dependency Mapping
- Legal Domain Adaptation
- Lexical search
- LLM
- Log probabilities
- LoRA
- Loss Function
- Machine Learning
- Metadata enrichment
- Metadata filtering
- Milvus
- Model Accountability
- Model Compression
- Model drift
- Model interpretability
- Model robustness
- Multi-Head Attention
- Multi-hop retrieval
- Multi-Jurisdictional Indexing
- Named Entity Recognition
- Nearest neighbor search
- Negative retrieval
- Neural Network
- OCR
- Ontology
- Passage retrieval
- Perplexity
- Pinecone
- Positional encoding
- Pretraining
- Privacy by design
- Prompt
- Prompt Injection
- Pruning
- QLoRA
- Quantization
- Query Expansion
- Query Intent
- Query rewriting
- Query Understanding
- Regression testing (AI systems)
- Regulatory Drift Detection
- Reinforcement Learning
- Relevance scoring
- Relevance Tuning
- Reliability metrics
- Reranking
- Responsible AI
- Retrieval coverage
- Retrieval Coverage Analysis
- Retrieval filtering
- Retrieval latency
- Retrieval layer
- Retrieval orchestration
- Retrieval pipeline
- Retrieval precision
- Retrieval recall
- Retrieval scoring
- Retrieval-Augmented Generation
- RLHF
- Role-based access control (RBAC)
- Schema markup
- Search Analytics
- Self-Attention
- Semantic clustering
- Semantic Expansion
- Semantic ranking
- Semantic Search
- Semantic Similarity
- SentencePiece
- Similarity search
- Sliding window chunking
- Source Conflict Resolution
- Source Freshness Tracking
- Source hierarchy
- Source provenance
- Source Reliability Weighting
- Sparse Retrieval
- Stress testing
- Structured data
- Structured output generation
- Supervised Learning
- System prompt
- Taxonomy (information architecture)
- Temperature
- Temporal indexing
- TF-IDF
- Tokenization
- Tool use in LLMs
- Top-k Sampling
- Top-p Sampling
- Transformer Architecture
- Uncertainty estimation
- Unsupervised Learning
- Vector Database
- Vector embeddings
- Vector indexing
- Vector normalization
- Vector quantization
- Version control in knowledge systems
- Weaviate
- WIB/CIR
- Zero-Shot Learning
Guides
- Belgian Corporate Income Tax: Rates, Deductions, and Compliance
- Belgian Inheritance and Gift Tax: Regional Rules Explained
- Belgian Personal Income Tax: Brackets, Deductions, and Filing
- Belgian VAT System: Registration, Rates, and Returns
- Complete Guide to the Belgian Tax on Stock Exchange Transactions (TOB)
Topics
- Belgium-France Double Taxation Treaty: Key Provisions
- Belgium-Netherlands Double Taxation Treaty: Key Provisions
- Inheritance Tax in Flanders: Rates and Exemptions
- Inheritance Tax in Wallonia: Rates and Exemptions
- TOB Rate on Bonds and Debt Securities
- TOB Rate on Shares and Equity Securities
- WIB Article 171: Separate Taxation of Certain Income
- WIB Article 215: Corporate Income Tax Rates