Skip to main content

Blog

AI in legal research, and Belgian tax law in practice

Explore glossary

The next frontiers in AI beyond scaling

The era of making models bigger is ending. Five paradigms are replacing brute-force scaling: hybrid architectures, inference-time reasoning, world models, self-improvement loops, and hardware co-design. What each means for AI in regulated industries.

AI architecture scaling laws hybrid models inference reasoning world models AI research Auryth

What is reranking, and why it's the difference between finding documents and finding answers

First-stage retrieval finds 100 matches. Reranking identifies the 5 that actually answer your question. Here's why that distinction matters for legal AI.

reranking cross-encoder legal AI retrieval search quality

How hybrid search works, and why your legal AI tool probably uses only half the equation

Keyword search finds exact article numbers. Semantic search finds related concepts. Hybrid search does both, and the difference is measurable.

hybrid search BM25 semantic search legal AI retrieval

What is a knowledge graph, and why it changes how AI navigates Belgian tax law

A search engine finds text. A knowledge graph navigates relationships: which article amends which, which ruling interprets what, which exception overrides the rule. Belgian tax law is a web of cross-references, and a knowledge graph is the map.

knowledge graph legal AI Belgian tax RAG cross-references NLP

What is chunking, and why it's the invisible foundation of legal AI quality

Before your legal AI tool can answer a question, it has to cut the law into pieces. The way it cuts determines whether the answer includes the exception that changes everything, or misses it entirely.

What is authority ranking, and why your legal AI tool probably ignores it

A ministerial circular and a Court of Cassation ruling look the same to most AI search systems. That is a fundamental gap, and it makes every answer unreliable.

authority ranking legal hierarchy RAG Belgian tax search architecture

What is RAG, and why it's not enough for legal AI on its own

How retrieval-augmented generation works, why basic RAG still hallucinates, and what a search-RAG fusion architecture adds for tax professionals.

Fine-tuning vs. RAG: two ways to make AI smart, and why it matters which one your tax tool chose

Fine-tuning memorizes yesterday's law. RAG looks up today's. For Belgian tax professionals, this architecture choice determines whether your AI tool is current or confidently outdated.

AI hallucinations: why ChatGPT fabricates sources (and how to spot it)

Why language models invent legal citations, what makes Belgian tax especially vulnerable, and three defenses that actually work.