用轻量向量精准控制LLM输出语言，不牺牲任务性能。
ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance
- 通过多语平行语料提取语言特异性向量，实现无监督语言引导。
- 在18种语言上验证，显著减少语言混淆且保持任务准确率。
- 适合需要多语言输出且不希望性能下降的研究者与开发者。
随着大语言模型日益支持多语言，它们常出现语言混淆问题，即生成答案的语言与用户提示或要求不符。本文提出ReCoVeR（REducing language COnfusion in VEctor Representations），一种基于语言特异性引导向量的轻量级方法。我们利用多语平行语料分离出语言向量，并通过固定（无监督）或可训练的引导函数实现有效语言控制。在三个基准测试和18种语言上的广泛评估表明，ReCoVeR在单语与跨语言场景下均能有效缓解语言混淆，同时相较以往方法，保持了任务性能。数据与代码已公开于https://github.com/hSterz/recover。
原文摘要 · Abstract (English)
As they become increasingly multilingual, Large Language Models (LLMs) exhibit more language confusion, i.e., they tend to generate answers in a language different from the language of the prompt or the answer language explicitly requested by the user. In this work, we propose ReCoVeR (REducing language COnfusion in VEctor Representations), a novel lightweight approach for reducing language confusion based on language-specific steering vectors. We first isolate language vectors with the help of multi-parallel corpus and then effectively leverage those vectors for effective LLM steering via fixed (i.e., unsupervised) as well as trainable steering functions. Our extensive evaluation, encompassing three benchmarks and 18 languages, shows that ReCoVeR effectively mitigates language confusion in both monolingual and cross-lingual setups while at the same time -- and in contrast to prior language steering methods -- retaining task performance. Our data code is available at https://github.com/hSterz/recover.
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。