Papers by Amin Mantrach
Multilingual Self-Taught Faithfulness Evaluators (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing faithfulness evaluation approaches are mostly English-focused and require expensive human-labeled training data for fine-tuning specialized models. |
| Approach: | They propose a framework that learns exclusively from synthetic multilingual data while leveraging cross-lingual transfer learning to improve an LLM's general language capabilities. |
| Outcome: | The proposed framework shows that it improves over existing baselines, including state-of-the-art English evaluators and machine translation-based approaches. |