A consistent body of evidence suggests that dream reports significantly vary
from other types of textual transcripts with respect to semantic content.
Furthermore, it appears to be a widespread belief in the dream/sleep research
community that dream reports constitute rather ``unique'' strings of text. This
might be a notable issue for the growing amount of approaches using natural
language processing (NLP) tools to automatically analyse dream reports, as they
largely rely on neural models trained on non-dream corpora scraped from the
web. In this work, I will adopt state-of-the-art (SotA) large language models
(LLMs), to study if and how dream reports deviate from other human-generated
text strings, such as Wikipedia. Results show that, taken as a whole, DreamBank
does not deviate from Wikipedia. Moreover, on average, single dream reports are
significantly more predictable than Wikipedia articles. Preliminary evidence
suggests that word count, gender, and visual impairment can significantly shape
how predictable a dream report can appear to the model.

本篇论文利用大型语言模型研究了梦境描述和其他人类生成文本的相似度，发现总体而言梦境描述并未与维基百科等非梦境语料有明显差异，且单个梦境描述比维基百科文章更易预测。同时，文章还发现词数、性别和视力障碍等因素可能会对梦境描述的可预测性产生显著影响。

梦境比你想象中更 “预测

Dreams Are More "Predictable'' Than You Think

In the field of dream research, the study of dream content typically relies
on the analysis of verbal reports provided by dreamers upon awakening from
their sleep. This task is classically performed through manual scoring provided
by trained annotators, at a great time expense. While a consistent body of work
suggests that natural language processing (NLP) tools can support the automatic
analysis of dream reports, proposed methods lacked the ability to reason over a
report's full context and required extensive data pre-processing. Furthermore,
in most cases, these methods were not validated against standard manual scoring
approaches. In this work, we address these limitations by adopting large
language models (LLMs) to study and replicate the manual annotation of dream
reports, using a mixture of off-the-shelf and bespoke approaches, with a focus
on references to reports' emotions. Our results show that the off-the-shelf
method achieves a low performance probably in light of inherent linguistic
differences between reports collected in different (groups of) individuals. On
the other hand, the proposed bespoke text classification method achieves a high
performance, which is robust against potential biases. Overall, these
observations indicate that our approach could find application in the analysis
of large dream datasets and may favour reproducibility and comparability of
results across studies.

采用大型语言模型来解决自然语言处理工具在梦境研究中的局限性，通过使用混合的现成和定制方法，特别关注情感参考，最终表明我们的方法可能在大型梦境数据集的分析中应用，并可能有利于研究结果的可重复性和比较性。