Mitigating Covertly Unsafe Text within Natural Language Systems

10/17/2022
by   Alex Mei, et al.
0

An increasingly prevalent problem for intelligent technologies is text safety, as uncontrolled systems may generate recommendations to their users that lead to injury or life-threatening consequences. However, the degree of explicitness of a generated statement that can cause physical harm varies. In this paper, we distinguish types of text that can lead to physical harm and establish one particularly underexplored category: covertly unsafe text. Then, we further break down this category with respect to the system's information and discuss solutions to mitigate the generation of text in each of these subcategories. Ultimately, our work defines the problem of covertly unsafe language that causes physical harm and argues that this subtle yet dangerous issue needs to be prioritized by stakeholders and regulators. We highlight mitigation strategies to inspire future researchers to tackle this challenging problem and help improve safety within smart systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/18/2022

SafeText: A Benchmark for Exploring Physical Safety in Language Models

Understanding what constitutes safe text is an important issue in natura...
research
12/19/2022

Foveate, Attribute, and Rationalize: Towards Safe and Trustworthy AI

Users' physical safety is an increasing concern as the market for intell...
research
09/15/2021

Challenges in Detoxifying Language Models

Large language models (LM) generate remarkably fluent text and can be ef...
research
03/08/2020

Formal Verification of Cyber-Physical Systems using Theorem Proving (Invited Paper)

Due to major breakthroughs in software and engineering technologies, emb...
research
09/15/2023

PoseFix: Correcting 3D Human Poses with Natural Language

Automatically producing instructions to modify one's posture could open ...
research
05/15/2022

Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy

Large pre-trained neural language models have supported the effectivenes...
research
11/12/2018

Automatically Generate Steganographic Text Based on Markov Model and Huffman Coding

Steganography, as one of the three basic information security systems, h...

Please sign up or login with your details

Forgot password? Click here to reset