Targeted Lexical Injection vs Full-Fine-Tuning for Cross-Lingual Representation Robustness in Low-Resource Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their performance in low-resource languages (LRLs), such as Swahili, often lags due to data scarcity and underrepresentation in pre-training. A key challenge is achieving robust cross-lingual lexical alignment, crucial for tasks like translation and cross-lingual information retrieval. This paper introduces Targeted Lexical Injection (TLI), a novel and efficient fine-tuning approach. We first demonstrate that Lugha-Llama-8B-wura, a Swahili-centric LLM, exhibits strong, near-perfect lexical alignment for Swahili-English
Research goal: How does Targeted Lexical Injection (TLI) compare to full-fine-tuning in terms of cross-lingual representation robustness on the XLAIR benchmark for low-resource languages?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.
Similar
Targeted Lexical Injection vs Full Fine-Tuning in Cross-Lingual Alignment for Lugha-LlamaParameter-Efficient Tuning vs. Full Fine-Tuning in Cross-Lingual Dense Retrieval for Low-Resource LanguagesTargeted Lexical Injection with Early-Layer LoRA Fine-Tuning for Low-Resource LanguagesEarly-Layer LoRA Fine-Tuning with Targeted Lexical Injection for Robustness in Low-Resource Lugha-LlamaEarly-Layer LoRA Fine-Tuning vs Full-Parameter Tuning for Zero-Shot Cross-Lingual Retrieval in Low-Resource LanguagesTargeted Lexical Injection for Zero-Shot Cross-Lingual Transfer in Low-Resource African Languages