تقرير
Self-Recognition in Language Models
العنوان: | Self-Recognition in Language Models |
---|---|
المؤلفون: | Davidson, Tim R., Surkov, Viacheslav, Veselovsky, Veniamin, Russo, Giuseppe, West, Robert, Gulcehre, Caglar |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
الوصف: | A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification methods, we propose a novel approach for assessing self-recognition in LMs using model-generated "security questions". Our test can be externally administered to keep track of frontier models as it does not require access to internal model parameters or output probabilities. We use our test to examine self-recognition in ten of the most capable open- and closed-source LMs currently publicly available. Our extensive experiments found no empirical evidence of general or consistent self-recognition in any examined LM. Instead, our results suggest that given a set of alternatives, LMs seek to pick the "best" answer, regardless of its origin. Moreover, we find indications that preferences about which models produce the best answers are consistent across LMs. We additionally uncover novel insights on position bias considerations for LMs in multiple-choice settings. Comment: Code to reproduce experiments and replicate findings is made available at https://github.com/trdavidson/self-recognition |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.06946 |
رقم الأكسشن: | edsarx.2407.06946 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |