inducing-regular-expressions-handful-labelled-examples-entity-spans-czech CLM-0254For inducing regular expressions from a handful of labelled examples (entity spans in Czech clinical notes), prompting an LLM and then iteratively refining the pattern against match failures extracts entities more accurately than genetic-programming regex induction, with the margin largest when few examples are available.
Capability: Writing a reusable locator: regex, SQL, XPath
Observed on
Regularly patterned clinical entities (dates, procedure data, events) in Czech clinical notes; comparison is against genetic-programming regex induction from examples..
Sources
- Validated by: Extraction performance on Czech clinical notes compared against state-of-the-art genetic-programming regex induction, varying the number of examples; the abstract reports outperformance but no numbers.. Only an abstract is available: it asserts outperformance on Czech clinical notes with no metrics, entity counts, model names, or baseline configuration reported. Single language, single domain, no ablation isolating the feedback loop from the initial prompt.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For synthesizing regexes from user intent, neither a natural-language description nor positive/negative examples alone is sufficient — descriptions are ambiguous and small example sets underdetermine the pattern — so a system that parses the description into a structural sketch and uses it to guide example-based search solves far more tasks than either modality alone (80% vs 43% NL-only and 26% examples-only on 300+ regexes).Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- When training a sequence-to-sequence model to generate regular expressions from natural language, rewarding semantic equivalence to the reference (checked by DFA equivalence and test cases) yields more semantically correct regexes than maximum-likelihood training on the reference string, because one intent has many syntactically different equivalent regexes.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- For translating English descriptions into regular expressions, a generic attention-based sequence-to-sequence model trained only on description/regex pairs matches a domain-engineered semantic parser on a small corpus (814 examples) and beats it by a wide margin once the training corpus is scaled to 10,000 pairs, with no semantic-equivalence machinery built in.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- When extracting structured rules from multimodal enterprise guideline documents, wrapping the extraction in deterministic schema validation, an LLM semantic judge, and a duplicate/contradiction consistency filter over a shared rule store lowers the share of extracted rules with no matching source sentence from about 15.7% to 3.2% relative to a one-pass pipeline using the same parser and models.Stating false facts confidently · reviewed by AI
- For structured extraction from text files, web pages and spreadsheets, a few user-highlighted example fields are enough to synthesise a reusable extraction program that pulls the remaining fields without further interaction — the locator can be inferred from examples rather than written or re-invoked per record.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: low. Falsifier as drafted: A matched comparison on the same clinical extraction tasks where genetic-programming regex induction equals or beats LLM prompting plus feedback refinement at low example counts.