Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
As Large Language Models (LLMs) become an important way of information seeking, there have been increasing concerns about the unethical content LLMs may generate. In this paper, we conduct a rigorous evaluation of LLMs' implicit bias towards certain groups by attacking them with carefully crafted instructions to elicit biased responses. Our attack methodology is inspired by psychometric principles in cognitive and social psychology. We propose three attack approaches, i.e., Disguise, Deception, and Teaching, based on which we built evaluation datasets for four common bias types. Each prompt attack has bilingual versions. Extensive evaluation of representative LLMs shows that 1) all three attack methods work effectively, especially the Deception attacks; 2) GLM-3 performs the best in defending our attacks, compared to GPT-3.5 and GPT-4; 3) LLMs could output content of other bias types when being taught with one type of bias. Our methodology provides a rigorous and effective way of evaluating LLMs' implicit bias and will benefit the assessments of LLMs' potential ethical risks.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A word association network methodology for evaluating implicit biases in LLMs compared to humans
As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often impli…
BiasKG: Adversarial Knowledge Graphs to Induce Bias in Large Language Models
Modern large language models (LLMs) have a significant amount of world knowledge, which enables strong performance in commonsense reasoning and knowledge-intensive tasks when harnessed properly. The language model can al…
Knowledge GraphsLanguage ModelingLanguage ModellingWorld KnowledgeUnveiling the Implicit Toxicity in Large Language Models
The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic o…
Language ModellingReinforcement Learning (RL)ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues
Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based pr…
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection
Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content. While extensive research has investigated bias in LLMs, prior work has predominantly focused on explicit …