extracting-fields-vertical-websites-decomposing-xpath-induction-into-separate CLM-0253For extracting fields from vertical websites, decomposing XPath induction into separate sub-tasks over a few seed pages lets an LLM emit an XPath that generalizes to unseen pages of the same site, beating single-prompt CoT and Reflexion XPath generation by 14.84-23.86 F1 points, while calling the model only a handful of times instead of once per page.
Capability: Writing a reusable locator: regex, SQL, XPath
Observed on
Vertical (single-template) websites with hierarchical HTML and repeated page structure; seed pages available for induction..
Sources
- Validated by: F1 on several structured web data extraction datasets against Reflexion and CoT prompting baselines; 14.84-23.86 point gains, with fewer LLM interactions.. Abstract-only evidence: reported F1 gains across multiple datasets versus two prompting baselines. No per-dataset numbers, no model list, and no ablation isolating which sub-task decomposition carries the gain.
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 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
- 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
- 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 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 LLM agents on long-horizon web penetration testing, holding the backbone model fixed and moving global state out of the context window onto a persistent graph of verified facts and fact-conditioned intent edges raises task success most on the hardest tasks, where success depends on facts obtained dozens of steps earlier (88.2% overall and 75.0% hard, vs 44.1% and 25.0% for the strongest shared-plain-text-memory baseline).Completing tasks that take many steps or many hours · 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: On the same vertical-website extraction datasets, decomposed XPath induction matches or falls below CoT/Reflexion F1, or its induced XPaths fail on unseen pages of the same site at rates comparable to per-page LLM extraction.