Indic-TunedLens：解读印度语言多语言模型
Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
AI总结：
Indic-TunedLens通过学习共享仿射变换，为印度语言提供更准确的模型表示解码，提升多语言模型的可解释性。
摘要：
多语言大语言模型（LLMs）正在越来越多地部署在语言多样性的地区，如印度，但大多数可解释性工具仍针对英语。先前的工作表明，LLMs往往在以英语为中心的表示空间中运行，使跨语言可解释性成为一个紧迫的问题。我们引入了Indic-TunedLens，这是一种专门针对印度语言的可解释性框架，它学习了共享的仿射变换。与标准的Logit Lens不同，后者直接解码中间激活，Indic-TunedLens为每个目标语言调整隐藏状态，使其与目标输出分布对齐，从而能够更忠实解码模型表示。我们评估了我们的框架在10种印度语言上使用MMLU基准，并发现它在SOTA可解释性方法上显著改进，尤其是对于形态丰富、资源有限的语言。我们的结果提供了关于多语言Transformer层间语义编码的重要见解。我们的模型可在https://huggingface.co/spaces/MihirRajeshPanchal/IndicTunedLens上获得。我们的代码可在https://github.com/MihirRajeshPanchal/IndicTunedLens上获得。
英文摘要：
Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior work reveals that LLMs often operate in English centric representation spaces, making cross lingual interpretability a pressing concern. We introduce Indic-TunedLens, a novel interpretability framework specifically for Indian languages that learns shared affine transformations. Unlike the standard Logit Lens, which directly decodes intermediate activations, Indic-TunedLens adjusts hidden states for each target language, aligning them with the target output distributions to enable more faithful decoding of model representations. We evaluate our framework on 10 Indian languages using the MMLU benchmark and find that it significantly improves over SOTA interpretability methods, especially for morphologically rich, low resource languages. Our results provide crucial insights into the layer-wise semantic encoding of multilingual transformers. Our model is available at https://huggingface.co/spaces/MihirRajeshPanchal/IndicTunedLens. Our code is available at https://github.com/MihirRajeshPanchal/IndicTunedLens.
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。
