MuCAL: Contrastive Alignment for Preference-Driven KG-to-Text Generation
Résumé
We propose MuCAL (Multilingual Contrastive Alignment Learning) to tackle the challenge of Knowledge Graphs (KG)-to-Text generation using preference learning, where reliable preference data is scarce. MuCAL is a multilingual KG/Text alignment model achieving robust cross-modal retrieval across multiple languages and difficulty levels. Building on Mu-CAL, we automatically create preference data by ranking candidate texts from three LLMs (Qwen2.5 , DeepSeek-v3, Llama-3). We then apply Direct Preference Optimisation (DPO) on these preference data, bypassing typical reward modelling steps to directly align generation outputs with graph semantics. Extensive experiments on KG-to-English Text generation show two main advantages: (1) Our KG/Text alignment model provides a better signal for DPO than similar existing metrics, and (2) significantly better generalisation on out-of-domain datasets compared to standard instruction tuning. Our results highlight MuCAL's effectiveness in supporting preference learning for KGto-English Text generation and lay the foundation for future multilingual extensions.
Domaines
| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|---|
| Licence |