相关论文: Bias Analysis and Mitigation through Protected Att…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has proposed debiasing methods that require human labelled examples,…

Large language models (LLMs) are known to exhibit biases in downstream tasks, especially when dealing with sensitive topics such as political discourse, gender identity, ethnic relations, or national stereotypes. Although significant…

Large Language Models (LLMs) are trained on massive, unstructured corpora, making it unclear which social patterns and biases they absorb and later reproduce. Existing evaluations typically examine outputs or activations, but rarely connect…

Biases and errors in human-labeled data present significant challenges for machine learning, especially in supervised learning reliant on potentially flawed ground truth data. These flaws, including diagnostic errors and societal biases,…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

LLMs are increasingly powerful and widely used to assist users in a variety of tasks. This use risks the introduction of LLM biases to consequential decisions such as job hiring, human performance evaluation, and criminal sentencing. Bias…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind…

Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…

The advent of Large Language Models (LLMs) has revolutionized product recommenders, yet their susceptibility to adversarial manipulation poses critical challenges, particularly in real-world commercial applications. Our approach is the…

We develop a statistical test to detect lookahead bias in economic forecasts generated by large language models (LLMs). Using state-of-the-art pre-training data detection techniques, we estimate the likelihood that a given prompt appeared…

In recent years, the rapid advancement of machine learning (ML) models, particularly transformer-based pre-trained models, has revolutionized Natural Language Processing (NLP) and Computer Vision (CV) fields. However, researchers have…

With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round self-improving methods allow LLMs to generate…

We test whether NLP datasets created with Large Language Models (LLMs) contain annotation artifacts and social biases like NLP datasets elicited from crowd-source workers. We recreate a portion of the Stanford Natural Language Inference…

Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open…

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Large Language Model (LLM)-based recommendation systems excel in delivering comprehensive suggestions by deeply analyzing content and user behavior. However, they often inherit biases from skewed training data, favoring mainstream content…