Dataset Viewer
Auto-converted to Parquet Duplicate
id
stringlengths
5
9
messages
listlengths
2
2
ner_1
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_4
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_3
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_10
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_27
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_26
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_15
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_16
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_39
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_50
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_52
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_48
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_44
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_12
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_13
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_68
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
ner_85
[ { "role": "user", "content": "You are generating high-quality synthetic reasoning data. This data will be used to train a small model to perform open-schema named entity recognition through explicit reasoning. Your role is the teacher: think through the task carefully and completely, because the small model...
End of preview. Expand in Data Studio

LLM-Jury Scores and Accepted Teacher Outputs

Part of the code, data and models of the bachelor thesis Structuring Universal Chain-of-thought for Named Entity Recognition (Department of Computer Science and Engineering, University of Bologna, 2026). All the repositories cited by name belong to the same organization.

Three judge LLMs, from different model families, independently scored every teacher extraction in teacher-cot-pile-ner against the Pile-NER gold, on two axes:

  • completeness: fraction of the gold spans meaningfully covered by the extraction;
  • correctness: fraction of the extra, non-gold entities that are justified by the text.
File Content
jury_scores_gemma-3-4b-it.jsonl scores of google/gemma-3-4b-it
jury_scores_DeepSeek-R1-Distill-Llama-8B.jsonl scores of deepseek-ai/DeepSeek-R1-Distill-Llama-8B
jury_scores_granite-4-1-8b.jsonl scores of ibm-granite/granite-4.1-8b
jury_filtered_train.jsonl the 6,895 accepted rows (mean completeness ≥ 0.6 and mean correctness ≥ 0.6), in the original open-schema chat format used for the first MedGemma SFT

Each score row has id, judge_model, completeness_score, completeness_notes, correctness_score, correctness_notes, raw_response.

Downloads last month
28