A Case Report On The "A.I. Locked-In Problem": social concerns with modern NLP

TL;DR

This paper discusses the 'Locked-In Problem' in modern NLP systems like GPT-3, where models become stuck in narratives, raising practical and social concerns about their conversational capabilities.

Contribution

It introduces the 'Locked-In Problem' as a new challenge in NLP, supported by an experimental case report and analysis of social implications.

Findings

GPT-3 can get stuck in narratives, hindering further interaction

The 'Locked-In Problem' affects practical usability of NLP models

Social concerns include manipulation and loss of control

Abstract

Modern NLP models are becoming better conversational agents than their predecessors. Recurrent Neural Networks (RNNs) and especially Long-Short Term Memory (LSTM) features allow the agent to better store and use information about semantic content, a trend that has become even more pronounced with the Transformer Models. Large Language Models (LLMs) such as GPT-3 by OpenAI have become known to be able to construct and follow a narrative, which enables the system to adopt personas on the go, adapt them and play along in conversational stories. However, practical experimentation with GPT-3 shows that there is a recurring problem with these modern NLP systems, namely that they can "get stuck" in the narrative so that further conversations, prompt executions or commands become futile. This is here referred to as the "Locked-In Problem" and is exemplified with an experimental case report, followed by practical and social concerns that are accompanied with this problem.