structured-extraction-text-files-web-pages-spreadsheets-few-user-highlighted CLM-0255For 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.
Capability: Writing a reusable locator: regex, SQL, XPath
Observed on
Semi-structured documents (text, web, spreadsheet) where the target fields are positionally or syntactically regular; user must supply and possibly correct highlights..
Sources
- Validated by: Not measured in the text available here; the source is a summary written from the title and a forwarder's note, not the paper's results.. Weak: no source text, abstract, metrics, or baseline available at ingestion. The claim restates the framework's premise rather than a measured result; needs verification against the actual paper before filing with confidence.
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 collections of template-generated pages, a delimiter-based extraction pattern induced from a handful of labelled examples can be reused across the rest of the collection, so extraction cost per page drops to pattern execution rather than per-page inference.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- For synthesizing reusable XPath extractors from a few sampled web pages, a two-stage pipeline — first having a cheaper model extract both the target value and the neighbouring cue text from an attribute-stripped HTML tree, then having a stronger model write the XPath over HTML condensed around those located nodes with an execution-feedback loop — reaches usable extraction F1 on multi-domain product/listing pages while keeping prompt size far below feeding raw pages.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 response-level hallucination detection in retrieval-augmented settings, having the model first convert the reference documents into a relational SQL database and then check the response against SELECT query results raises precision and macro F1 over zero-shot direct prediction, over atomic-claim decomposition, and over flat JSON key-value extraction, without any task-specific fine-tuning.Stating false facts confidently · reviewed by AI
- 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
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: Show that on typical semi-structured documents, programs synthesised from a handful of highlighted examples fail to extract the remaining fields at usable precision, so per-record extraction is still required.