Text Classification
Transformers
Safetensors
English
modernbert
fact-verification
claim-verification
reward-model
llm-as-a-judge
distillation
decomposition
faithfulness
answer-verification
text-embeddings-inference
Instructions to use dipta007/answer-judge-balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dipta007/answer-judge-balanced with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dipta007/answer-judge-balanced")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("dipta007/answer-judge-balanced") model = AutoModelForSequenceClassification.from_pretrained("dipta007/answer-judge-balanced") - Notebooks
- Google Colab
- Kaggle
Use official arXiv paper title in citation
Browse files
README.md
CHANGED
|
@@ -114,7 +114,7 @@ DecomposeRL trains a claim-verification policy with GRPO over a seven-reward ens
|
|
| 114 |
|
| 115 |
```bibtex
|
| 116 |
@article{dipta2025decomposerl,
|
| 117 |
-
title={DecomposeRL:
|
| 118 |
author={Shubhashis Roy Dipta and Ankur Padia and Francis Ferraro},
|
| 119 |
year={2025},
|
| 120 |
eprint={2605.27858},
|
|
|
|
| 114 |
|
| 115 |
```bibtex
|
| 116 |
@article{dipta2025decomposerl,
|
| 117 |
+
title={DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification},
|
| 118 |
author={Shubhashis Roy Dipta and Ankur Padia and Francis Ferraro},
|
| 119 |
year={2025},
|
| 120 |
eprint={2605.27858},
|