paper-with-me

홈 › Papers

Quantitative Certification of Bias in Large Language Models

2024-05-29 · Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta, Gagandeep Singh

Large Language Models (LLMs) can produce biased responses that can cause representational harms. However, conventional studies are insufficient to thoroughly evaluate LLM bias, as they can not scale to large number of inputs and provide no guarantees. Therefore, we propose the first framework, QuaCer-B that certifies LLMs for bias on distributions of prompts. A certificate consists of high-confidence bounds on the probability of unbiased LLM responses for any set of prompts mentioning various demographic groups, sampled from a distribution. We illustrate the bias certification for distributions of prompts created by applying varying prefixes drawn from a prefix distributions, to a given set of prompts. We consider prefix distributions for random token sequences, mixtures of manual jailbreaks, and jailbreaks in the LLM's embedding space to certify bias. We obtain non-trivial certified bounds on the probability of unbiased responses of SOTA LLMs, exposing their vulnerabilities over distributions of prompts generated from computationally inexpensive distributions of prefixes.

📄 PDF Abstract BibTeX arXiv:2405.18780

Code (1)

uiuc-focal-lab/quacer-b 공식 구현

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Fairness Certification for Natural Language Processing and Large Language Models

2024-01-02 · Vincent Freiberger, Erik Buchmann

Natural Language Processing (NLP) plays an important role in our daily lives, particularly due to the enormous progress of Large Language Models (LLM). However, NLP has many fairness-critical use cases, e.g., as an exper…

Fairness

Robust Certification for Laplace Learning on Geometric Graphs

2021-04-22 · Matthew Thorpe, Bao Wang

Graph Laplacian (GL)-based semi-supervised learning is one of the most used approaches for classifying nodes in a graph. Understanding and certifying the adversarial robustness of machine learning (ML) algorithms has att…

Adversarial AttackAdversarial Robustness

Certifying the Fairness of KNN in the Presence of Dataset Bias

2023-07-17 · Yannan Li, Jingbo Wang, Chao Wang

We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, the k-nearest neighbors (KNN), under the assumption that the training data may have historical …

Fairness

Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study

2026-06-29 · Mirko Perkusich, Danyllo Albuquerque, João Paiva, Robson Vilar 외 arxiv

Large Language Models (LLMs) are increasingly used in Agile Software Development for documentation, coaching, and training. As practitioners adopt these tools to prepare for certifications such as Professional Scrum Mast…

Perfectly Parallel Fairness Certification of Neural Networks

2019-12-05 · Caterina Urban, Maria Christakis, Valentin Wüstholz, Fuyuan Zhang

Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools an…

Decision MakingFairness