Skip to content

For rebuttal, add GLiNER2 eval results#102

Open
Ki-Seki wants to merge 2 commits into
rebuttal/gliner2from
rebuttal/gliner2-results
Open

For rebuttal, add GLiNER2 eval results#102
Ki-Seki wants to merge 2 commits into
rebuttal/gliner2from
rebuttal/gliner2-results

Conversation

@Ki-Seki
Copy link
Copy Markdown
Member

@Ki-Seki Ki-Seki commented Apr 10, 2026

No description provided.

Copilot AI review requested due to automatic review settings April 10, 2026 18:09
@Ki-Seki Ki-Seki changed the title Add GLiNER2 eval results For rebuttal, add GLiNER2 eval results Apr 10, 2026
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds evaluation artifacts for the GLiNER2 CV-parsing run, capturing both the exact invocation used and the resulting per-item/aggregate metrics for later comparison and reproducibility.

Changes:

  • Added a full CV parsing evaluation result JSON for fastino/gliner2-large-v1 on Sculpt-AI/GIMBench-cv-parse.
  • Added a small eval.sh helper script to rerun the same evaluation configuration.

Reviewed changes

Copilot reviewed 1 out of 2 changed files in this pull request and generated 2 comments.

File Description
results/260411-kdd-rebuttal-cv-gliner2-model/fastino_gliner2-large-v1_Sculpt-AI_GIMBench-cv-parse_260411-010729.json Stores the recorded environment/args plus detailed per-item extraction outcomes and aggregate accuracy.
results/260411-kdd-rebuttal-cv-gliner2-model/eval.sh Provides a reproducible command to rerun the GLiNER2 CV parsing evaluation.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +85 to +97
"phone_number": {
"prediction": "",
"expected": "+49 (0) 621 181 2098",
"verbatim_correct": false,
"judge_model_correct": false,
"correct": false
},
"email": {
"prediction": "B n.zhang@uni-mannheim.de",
"expected": "n.zhang@uni-mannheim.de",
"verbatim_correct": false,
"judge_model_correct": false,
"correct": false
Comment on lines +1 to +6
python -m gimbench.cv.cv_parse \
--use_gliner2 \
--model_name "fastino/gliner2-large-v1" \
--model_type "openai" \
--judge_model_name "google/gemini-2.5-flash" \
--api_key $API_KEY --base_url $API_BASE
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants