Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
- URL: http://arxiv.org/abs/2406.14023v1
- Date: Thu, 20 Jun 2024 06:42:08 GMT
- Title: Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
- Authors: Yuchen Wen, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng,
- Abstract summary: We conduct a rigorous evaluation of Large Language Models' implicit bias towards certain groups by attacking them with carefully crafted instructions to elicit biased responses.
We propose three attack approaches, i.e., Disguise, Deception, and Teaching, based on which we built evaluation datasets for four common bias types.
- Score: 66.34066553400108
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: 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.
Related papers
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors [64.9938658716425]
Existing evaluations of large language models' (LLMs) ability to recognize and reject unsafe user requests face three limitations.
First, existing methods often use coarse-grained of unsafe topics, and are over-representing some fine-grained topics.
Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
Third, existing evaluations rely on large LLMs for evaluation, which can be expensive.
arXiv Detail & Related papers (2024-06-20T17:56:07Z) - Large Language Models Show Human-like Social Desirability Biases in Survey Responses [12.767606361552684]
We show that Large Language Models (LLMs) skew their scores towards the desirable ends of trait dimensions when personality evaluation is inferred.
This bias exists in all tested models, including GPT-4/3.5, Claude 3, Llama 3, and PaLM-2.
reverse-coding all the questions decreases bias levels but does not eliminate them, suggesting that this effect cannot be attributed to acquiescence bias.
arXiv Detail & Related papers (2024-05-09T19:02:53Z) - Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs [6.090496490133132]
We propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF.
We utilize LLMs in multi-role debates to create a dataset that includes both high-bias and low-bias instances for training the reward model in reinforcement learning.
arXiv Detail & Related papers (2024-04-15T22:18:50Z) - ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy.
It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
arXiv Detail & Related papers (2024-04-06T15:01:47Z) - Cognitive Bias in Decision-Making with LLMs [19.87475562475802]
Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks.
LLMs have been shown to inherit societal biases against protected groups, as well as be subject to bias functionally resembling cognitive bias.
Our work introduces BiasBuster, a framework designed to uncover, evaluate, and mitigate cognitive bias in LLMs.
arXiv Detail & Related papers (2024-02-25T02:35:56Z) - Coercing LLMs to do and reveal (almost) anything [80.8601180293558]
It has been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements.
We argue that the spectrum of adversarial attacks on LLMs is much larger than merely jailbreaking.
arXiv Detail & Related papers (2024-02-21T18:59:13Z) - Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment [8.948475969696075]
Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems.
We show that short universal adversarial phrases can be deceived to judge LLMs to predict inflated scores.
It is found that judge-LLMs are significantly more susceptible to these adversarial attacks when used for absolute scoring.
arXiv Detail & Related papers (2024-02-21T18:55:20Z) - Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others.
We formally define LLM's self-bias - the tendency to favor its own generation.
We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
arXiv Detail & Related papers (2024-02-18T03:10:39Z) - GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language
Models [83.30078426829627]
Large language models (LLMs) have gained popularity and are being widely adopted by a large user community.
The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability.
We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
arXiv Detail & Related papers (2023-12-11T12:02:14Z) - Goal-Oriented Prompt Attack and Safety Evaluation for LLMs [43.93613764464993]
We introduce a pipeline to construct high-quality prompt attack samples, along with a Chinese prompt attack dataset called CPAD.
Our prompts aim to induce LLMs to generate unexpected outputs with several carefully designed prompt attack templates.
The results show that our prompts are significantly harmful to LLMs, with around 70% attack success rate to GPT-3.5.
arXiv Detail & Related papers (2023-09-21T07:07:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.