synthesizing-reusable-xpath-extractors-few-sampled-web-pages-two-stage CLM-0257For 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.
Capability: Writing a reusable locator: regex, SQL, XPath
Observed on
Semi-structured HTML detail pages of the SWDE kind (90 sites, 9 domains), 3 seed pages per site, up to 3 evaluator feedback rounds; DeepSeek/GPT-4o/Claude backbones..
Sources
- Validated by: Set-matching precision/recall/F1/accuracy on SWDE across four backbones (best: GPT-4o, F1 0.8514, accuracy 0.7413); sanitization measured to cut page size to roughly 10-20%. Comparison to AutoCrawler is discussed narratively, not tabulated, and no ablation isolates the cue-text component.. [truncated]
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 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.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 small open-weight backbones (Qwen3-4B) driving long-horizon remote-sensing tool chains, inserting a step-level verifier that checks each intermediate tool output against schema, sub-goal and domain constraints and triggers replanning is the single largest architectural gain, while hierarchical decomposition without domain-aligned tool grouping adds little and can lower final accuracy relative to a flat agent with the same verifier.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: An ablation on the same dataset showing that dropping cue-text extraction, or feeding the sanitized page directly to the XPath-writing model, yields equal or better F1 at similar token cost.