Cross-Lingual Knowledge Augmentation for Mitigating Generic Overgeneralization in Multilingual Language Models

Ralethe, Sello and Buys, Jan (2025) Cross-Lingual Knowledge Augmentation for Mitigating Generic Overgeneralization in Multilingual Language Models, Proceedings of 5th Multilingual Representation Learning Workshop, November 2025, Suzhou, China, Association for Computational Linguistics.

[thumbnail of PDF] Other (PDF)
Association_for_Computational_Linguistics__ACL__multilingual_generics.pdf - Accepted Version
Download (159kB)

Abstract

Generic statements like “birds fly” or “lions have manes” express generalizations about kinds that allow exceptions, yet language models tend to overgeneralize them to universal claims. While previous work showed that ASCENT KB could reduce this effect in English by 30-40%, the effectiveness of broader knowledge sources and the cross-lingual nature of this phenomenon remain unexplored. We investigate generic overgeneralization across English and four South African languages (isiZulu, isiXhosa, Sepedi, SeSotho), comparing the impact of ConceptNet and DBpedia against the previously used ASCENT KB. Our experiments show that ConceptNet reduces overgeneralization by 45-52% for minority characteristic generics, while DBpedia achieves 48-58% for majority characteristics, with combined knowl- edge bases reaching 67% reduction. These improvements are consistent across all languages, though Nguni languages show higher baseline overgeneralization than Sotho-Tswana languages, potentially suggesting that morphological features may influence this semantic bias. Our findings demonstrate that commonsense and encyclopedic knowledge provide complementary benefits for multilingual semantic understanding, offering insights for developing NLP systems that capture nuanced semantics in low-resource languages.

Item Type: Conference paper
Subjects: Computing methodologies > Artificial intelligence > Natural language processing
Computing methodologies > Artificial intelligence > Knowledge representation and reasoning
Date Deposited: 17 Oct 2025 06:20
Last Modified: 17 Oct 2025 06:20
URI: https://pubs.cs.uct.ac.za/id/eprint/1762

Actions (login required)

View Item View Item