SyncAI.news, a Varaisys broadcasting
Is a Description Worth a Thousand Demonstrations? Specificity and Reliability of Task Descriptions in In-Context Learning
BN

Bruce Nguyen, Bei Jiang, Linglong Kong

· 1 min read

ResearcharXiv cs.LG

Is a Description Worth a Thousand Demonstrations? Specificity and Reliability of Task Descriptions in In-Context Learning

arXiv:2611.25560v1 Announce Type: new Abstract: A prompt for in-context learning (ICL) can describe a task in addition to, or instead of, demonstrating it through examples. Yet how task descriptions work remains poorly understood theoretically. Through the Bayesian view of ICL, we model descriptions as informative priors characterized by their specificity and reliability. We adapt the effective sample size (ESS) from Bayesian statistics, quantifying a description's predictive value as an equivalent number of demonstrations. For in-context linear regression, we show that a reliable description's ESS grows with its specificity and with the task's dimension. A description that may be irrelevant, however, gains little from its specificity unless demonstrations are given. In practice, do in-context learners use descriptions as a Bayes-optimal predictor would? Our experiments show that meta-trained Transformers come close to the Bayes-optimal ESS when tested on their training distribution. Pretrained language models, however, make too little use of highly specific descriptions when answering without reasoning; most of them closely match the Bayes-optimal predictor only when reasoning is enabled. These results extend the Bayesian analysis of ICL from demonstrations to descriptions.

Original source

This story was published by arXiv cs.LG and written by Bruce Nguyen, Bei Jiang, Linglong Kong. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News