Add pipeline tag and library name
Browse filesThis PR improves the model card by adding the `text-classification` pipeline tag and identifying the `transformers` library. It also links the model repository to its associated paper: [BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation](https://huggingface.co/papers/2604.09497).
README.md
CHANGED
|
@@ -1,15 +1,20 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
datasets:
|
| 3 |
- hgissbkh/BERTJudge-Dataset
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
-
|
| 7 |
-
|
| 8 |
---
|
|
|
|
| 9 |
# BERTJudge
|
| 10 |
|
| 11 |
BERT-as-a-Judge is a family of encoder-based models designed for efficient, reference-based evaluation of LLM outputs. Moving beyond rigid lexical extraction and matching, these models evaluate semantic correctness, accommodating variations in phrasing and formatting while using only a fraction of the computational resources required by LLM-as-a-Judge approaches.
|
| 12 |
|
|
|
|
|
|
|
| 13 |
## Model Summary
|
| 14 |
- **Paper:** [BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation](https://arxiv.org/abs/2604.09497)
|
| 15 |
- **Code:** [https://github.com/artefactory/BERT-as-a-Judge](https://github.com/artefactory/BERT-as-a-Judge)
|
|
@@ -88,7 +93,7 @@ If you find this model useful for your research, please consider citing:
|
|
| 88 |
```
|
| 89 |
@article{gisserotboukhlef2026bertasajudgerobustalternativelexical,
|
| 90 |
title={BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation},
|
| 91 |
-
author={Gisserot-Boukhlef, Hippolyte and Boizard, Nicolas and Malherbe, Emmanuel and Hudelot, C{\'e}line and Colombo, Pierre},
|
| 92 |
year={2026},
|
| 93 |
eprint={2604.09497},
|
| 94 |
archivePrefix={arXiv},
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- EuroBERT/EuroBERT-210m
|
| 4 |
datasets:
|
| 5 |
- hgissbkh/BERTJudge-Dataset
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
+
library_name: transformers
|
| 9 |
+
pipeline_tag: text-classification
|
| 10 |
---
|
| 11 |
+
|
| 12 |
# BERTJudge
|
| 13 |
|
| 14 |
BERT-as-a-Judge is a family of encoder-based models designed for efficient, reference-based evaluation of LLM outputs. Moving beyond rigid lexical extraction and matching, these models evaluate semantic correctness, accommodating variations in phrasing and formatting while using only a fraction of the computational resources required by LLM-as-a-Judge approaches.
|
| 15 |
|
| 16 |
+
This model was introduced in the paper [BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation](https://huggingface.co/papers/2604.09497).
|
| 17 |
+
|
| 18 |
## Model Summary
|
| 19 |
- **Paper:** [BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation](https://arxiv.org/abs/2604.09497)
|
| 20 |
- **Code:** [https://github.com/artefactory/BERT-as-a-Judge](https://github.com/artefactory/BERT-as-a-Judge)
|
|
|
|
| 93 |
```
|
| 94 |
@article{gisserotboukhlef2026bertasajudgerobustalternativelexical,
|
| 95 |
title={BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation},
|
| 96 |
+
author={Gisserot-Boukhlef, Hippolyte and Boizard, Nicolas and Malherbe, Emmanuel and Hudelot, C{\\'e}line and Colombo, Pierre},
|
| 97 |
year={2026},
|
| 98 |
eprint={2604.09497},
|
| 99 |
archivePrefix={arXiv},
|