WebSRC
WebSRC: A Dataset for Web-Based Structural Reading Comprehension
WebSRC is a novel Web-based Structural Reading Comprehension dataset.
How to run
$ npm i -g lettokenburn-cli$ ltb bench info websrc
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
1 sourced entry| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| ChatGPT 3.5 SpatialFormat | 80.7 | N/A | Independent | medium | Feb 15, 2024 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsAbout
WebSRC is a novel Web-based Structural Reading Comprehension dataset. It consists of 0.44M question-answer pairs, which are collected from 6.5K web pages with corresponding HTML source code, screenshots and metadata. Each question in WebSRC requires a certain structural understanding of a web page to answer, and the answer is either a text span on the web page or yes/no.
Source: WebSRC Homepage