Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm

Guardado en:
書目詳細資料
發表在:arXiv.org (Dec 24, 2024), p. n/a
主要作者: Hu, Xiaoyang
其他作者: Lewis, Richard L
出版:
Cornell University Library, arXiv.org
主題:
在線閱讀:Citation/Abstract
Full text outside of ProQuest
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
Resumen:Cognitive tasks originally developed for humans are now increasingly used to study language models. While applying these tasks is often straightforward, interpreting their results can be challenging. In particular, when a model underperforms, it's often unclear whether this results from a limitation in the cognitive ability being tested or a failure to understand the task itself. A recent study argued that GPT 3.5's declining performance on 2-back and 3-back tasks reflects a working memory capacity limit similar to humans. By analyzing a range of open-source language models of varying performance levels on these tasks, we show that the poor performance instead reflects a limitation in task comprehension and task set maintenance. In addition, we push the best performing model to higher n values and experiment with alternative prompting strategies, before analyzing model attentions. Our larger aim is to contribute to the ongoing conversation around refining methodologies for the cognitive evaluation of language models.
ISSN:2331-8422
Fuente:Engineering Database