Related papers: Shakespeare, Entropy and Educated Monkeys
Written language is a complex communication signal capable of conveying information encoded in the form of ordered sequences of words. Beyond the local order ruled by grammar, semantic and thematic structures affect long-range patterns in…
We demonstrate that small pretrained foundational generative language models with millions of parameters can learn the latent rules of a process from data associated with the process. Inspired by Stefan Zweig's novella "Schachnovelle," also…
A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the…
Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies…
Entities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a pan is hot) or on event reasoning (e.g., whether one would…
Writing is a cognitively demanding activity that requires constant decision-making, heavy reliance on working memory, and frequent shifts between tasks of different goals. To build writing assistants that truly align with writers'…
While extensive research has focused on ChatGPT in recent years, very few studies have systematically quantified and compared linguistic features between human-written and artificial intelligence (AI)-generated language. This exploratory…
Automated reasoning about uncertain knowledge has many applications. One difficulty when developing such systems is the lack of a completely satisfactory integration of logic and probability. We address this problem directly. Expressive…
Given the prevalence of crowd sourced labor in creating Natural Language processing datasets, these aforementioned sets have become increasingly large. For instance, the SQUAD dataset currently sits at over 80,000 records. However, because…
Recently we discovered (cond-mat/0212043) that the majority of scientific citations are copied from the lists of references used in other papers. Here we show that a model, in which a scientist picks three random papers, cites them,and also…
In the year 1876 the mathematician Charles Dodgson, who wrote fiction under the now more famous name of Lewis Carroll, devised a beautiful voting system that has long fascinated political scientists. However, determining the winner of a…
A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). The model was trained on…
The ability to persuade others is critical to professional and personal success. However, crafting persuasive messages is demanding and poses various challenges. We conducted nine exploratory case studies to identify adaptations that…
The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. While recent research has…
As generative AI tools like ChatGPT enter classrooms, workplaces and everyday thinking, writing is at risk of becoming a formality -- outsourced, automated and stripped of its cognitive value. But writing is not just output; it is how we…
Conversational participants tend to immediately and unconsciously adapt to each other's language styles: a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their…
Selection theory requires multiple, distinct, simultaneously-actualized states. In cognition, each thought or cognitive state changes the 'selection pressure' against which the next is evaluated; they are not simultaneously selected…
We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game. Specifically, we consider three competing goals for effective communication: use as few tokens as…
With the help of online tools, unscrupulous authors can today generate a pseudo-scientific article and attempt to publish it. Some of these tools work by replacing or paraphrasing existing texts to produce new content, but they have a…
Children have less text understanding capability than adults. Moreover, this capability differs among the children of different ages. Hence, automatically predicting a recommended age based on texts or sentences would be a great benefit to…