Communication Dans Un Congrès Année : 2025

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.

Mots clés

Fichier principal
Vignette du fichier
2025.emnlp-main.720.pdf (1.64 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05404224 , version 1 (09-12-2025)

Licence

Identifiants

Citer

Yifei Song, Claire Gardent. MuCAL: Contrastive Alignment for Preference-Driven KG-to-Text Generation. The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Nov 2025, Suzhou, China. pp.14238-14281, ⟨10.18653/v1/2025.emnlp-main.720⟩. ⟨hal-05404224⟩
155 Consultations
92 Téléchargements

Altmetric

Partager

  • More