引导大语言模型进行机器翻译个性化
Steering Large Language Models for Machine Translation Personalization
AI总结：
本文探讨在少量示例下如何个性化自动翻译，聚焦文学翻译领域，通过对比引导与稀疏自编码器（SAE）潜变量实现稳健的风格条件和翻译质量，提升推理效率。
摘要：
大型语言模型简化了符合预定义风格约束的个性化翻译生成。然而，当风格要求隐含在示例集中时，如特定人类译者生成的文本，这些系统仍面临挑战。本文探索了在少量示例下个性化自动翻译的策略，重点在文学翻译领域。我们首先确定任务可行性及风格信息在模型表示中的编码方式。然后评估各种提示策略和推理时干预，引导模型生成个性化风格，特别关注对比引导与稀疏自编码器（SAE）潜变量以识别显著的个性化属性。我们证明对比SAE引导能产生稳健的风格条件和翻译质量，比提示方法更高效。进一步研究引导对模型激活的影响，发现编码个性化属性的层受提示和SAE引导影响相似，表明存在相似机制。
英文摘要：
Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of examples, such as texts produced by a specific human translator. In this work, we explore various strategies for personalizing automatically generated translations when few examples are available, with a focus on the challenging domain of literary translation. We begin by determining the feasibility of the task and how style information is encoded within model representations. Then, we evaluate various prompting strategies and inference-time interventions for steering model generations towards a personalized style, with a particular focus on contrastive steering with sparse autoencoder (SAE) latents to identify salient personalization properties. We demonstrate that contrastive SAE steering yields robust style conditioning and translation quality, resulting in higher inference-time computational efficiency than prompting approaches. We further examine the impact of steering on model activations, finding that layers encoding personalization properties are impacted similarly by prompting and SAE steering, suggesting a similar mechanism at play.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
