不微调就能减少大模型生成非英文时的语言混淆。
Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning
- 通过针对性调整目标语言词汇的表示，实现无微调的跨语言对齐。
- 在多语言摘要任务中显著降低语言混淆率，保持原文摘要质量。
- 适合追求低成本多语言生成的开发者与研究者使用。
大型语言模型（LLMs）在生成非英文文本时有时会出现语言混淆。现有方法通常依赖微调来缓解此问题。本文提出一种无需微调的范式：引入语言感知令牌增强（LATB），对目标语言相关令牌施加定向扰动；以及自适应语言感知令牌增强（Adaptive-LATB），根据模型对目标语言的信心动态调整扰动强度。实验表明，该方法有效提升多语言一致性，显著降低语言混淆，同时保持摘要质量，且无需任何额外微调。代码已公开：https://github.com/scbdatax/genai-datax-language-aware-token-boosting。
原文摘要 · Abstract (English)
Large language models (LLMs) sometimes exhibit language confusion when generating non-English text. Existing approaches typically rely on fine-tuning to mitigate this issue. In contrast, we propose a tuning-free paradigm for reducing language confusion. Within this paradigm, we introduce two methods: Language-Aware Token Boosting (LATB), which applies targeted perturbations to tokens associated with the desired language, and Adaptive Language-Aware Token Boosting (Adaptive-LATB), which dynamically adjusts these perturbations based on the model's confidence in the intended language. Experiments demonstrate that our methods effectively improve multilingual alignment by reducing language confusion, while maintain the summarization quality without requiring any additional fine-tuning. Our code is publicly available. https://github.com/scbdatax/genai-datax-language-aware-token-boosting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。