EFTA Court Case Law Search

What this is

A search and analysis tool over the full corpus of EFTA Court judgments (1994 — present), built by Daniel Naurin, Professor of Political Science at the University of Oslo.

You can ask doctrinal questions in natural language ("What is the Court's approach to state aid?"), filter the corpus by subject area / country / case type / date, or run literal term-searches (search for "posting of workers"). Answers cite specific paragraphs that open the underlying judgment when you click them.

How to ask

The system picks one of five answer modes from the phrasing of the question. Answers are labelled with their mode and end with a tip for switching when another mode fits better.

• Doctrinal synthesis — how the case law fits together on a legal question, with paragraph citations. Ask about the law: "What is the Court's approach to proportionality in gambling cases?", "Provide a summary of the case law on public procurement".
• Case-by-case summaries — a standalone headnote per judgment. Use an exhaustive quantifier: "Summarise all judgments concerning public procurement", "summarise each of the state aid cases". Summaries come 3 per reply (up to 5 if you name the number); the rest are listed for follow-up.
• Lists, counts and filters — pure metadata, instant: "List advisory opinions from Norway since 2015", "How many pending cases are there?"
• Exact term search — literal full-text matching: search for "homogeneity". Quote a phrase to force an exact match.
• Single case lookup — "Summarise E-16/16", "What is E-9/97 about?", or just the case number.

Follow-up questions understand context ("which of these is most recent?" after a list). When words in a question cannot be mapped to a filter, the answer says so and suggests a term search instead.

What data the system has

• 359 EFTA Court judgments, advisory opinions, and orders
• 23,020 numbered paragraphs, individually indexed and embedded
• Most recent judgment in the corpus: 3 July 2026
• Source: official PDFs from eftacourt.int. Text is extracted, cleaned, and re-parsed into structured sections.

Known limitations

Coverage

• Language: English versions only.
• Document type: judgments and advisory opinions are fully indexed; orders and procedural documents less so. Some early-1990s orders have no Findings of the Court section by their nature and produce empty results for substantive questions.
• Date: the corpus is refreshed automatically each day (06:00 Europe/Oslo). New EFTA Court judgments are picked up within a day of publication on eftacourt.int. See "Most recent judgment" above for the most recently published case currently indexed. A separate Pending cases page lists cases lodged at the Court but not yet decided.

Retrieval and answer quality

• The system uses hybrid retrieval (semantic embeddings + keyword search + citation network + subject metadata) followed by a per-case LLM extractor that pulls out the Court's findings on the specific question. Answers cite paragraphs explicitly so you can verify each claim against source text.
• Citation faithfulness is the legal-QA failure mode to watch for: an answer may cite paragraph N for a proposition that paragraph N doesn't actually support. Always read the cited paragraph in the reading panel before relying on the claim.
• Party-argument confusion: the Court's reasoning section sometimes summarises a party's submission before rejecting it. The system tries to attribute accordingly, but occasionally mis-attributes a party's view to the Court. Verify before relying on an attribution.
• Cross-cutting doctrinal concepts (proportionality, legitimate expectations, legal certainty, direct effect) may produce empty answers because the Court applies these principles contextually rather than articulating general doctrinal statements. The system will tell you plainly when this is the case and suggest a term search.
• Cost-bounded extraction: for each question, the system extracts findings from a bounded set of cases (currently up to ~16 for broad subject queries). The "Coverage" line at the bottom of each answer reports the funnel: how many cases were considered, how many produced substantive findings, how many additional cases are listed in "See also" for further exploration.

What this is not

• Not a substitute for reading the judgments. Every assertion in an answer is backed by a citation to a specific paragraph. Click through and read the source text before relying on a proposition for advice or argument.
• Not legal advice. The system is descriptive — what the Court has said. It is not normative — what the law is or should be on a given set of facts. It does not substitute for legal counsel.
• Not a citator. The system does not track whether a finding has been overruled, distinguished, or confirmed in later cases. Treat every citation as a starting point.

Privacy

• Queries are logged so we can improve the system, identify retrieval failures, and (with expert-validator users) build a gold evaluation set. Logs include the query text, the retrieved case set, the generated answer, and any rating you submit.
• Your user identity is stored as a one-way HMAC of an opaque internal ID — your email and name are kept in a separate authentication store and are not joined to query logs in routine analysis.
• Do not enter confidential information. Treat the system as you would a colleague's lookup — useful for research and orientation, not for matters covered by professional confidentiality.
• Full details — what is stored, retention periods, and your rights — in the privacy notice.

Feedback

• Use the thumbs-up / thumbs-down buttons below each answer to flag whether the answer was helpful overall.
• Expert validators see additional rating widgets next to each cited paragraph (relevance 0-3, with optional note) and a three-axis answer rating (correctness, completeness, citation support). Ratings save automatically.
• For anything else, email daniel.naurin@stv.uio.no.