Related papers: How Implicit Bias Accumulates and Propagates in LL…
Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates…
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 proxies to detect…
Large Language Models (LLMs) push the bound-aries in natural language processing and generative AI, driving progress across various aspects of modern society. Unfortunately, the pervasive issue of bias in LLMs responses (i.e., predictions)…
Large language models (LLMs) are increasingly used in clinical settings, raising concerns about racial bias in both generated medical text and clinical reasoning. Existing studies have identified bias in medical LLMs, but many focus on…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be comprehensively collected…
Large Language Models (LLMs) excel at human-like language generation but often embed and amplify implicit, intersectional biases, especially under persona-driven contexts. Existing bias audits rely on static, embedding-based tests (CEAT,…
Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes decision-making (e.g., hiring and healthcare), mitigating…
With the advance of Artificial Intelligence (AI), Large Language Models (LLMs) have gained prominence and been applied in diverse contexts. As they evolve into more sophisticated versions, it is essential to assess whether they reproduce…
Recent works have showcased the ability of LLMs to embody diverse personas in their responses, exemplified by prompts like 'You are Yoda. Explain the Theory of Relativity.' While this ability allows personalization of LLMs and enables human…
Generative AI technologies, particularly Large Language Models (LLMs), have transformed information management systems but introduced substantial biases that can compromise their effectiveness in informing business decision-making. This…
Large Language Models (LLMs), though shown to be effective in many applications, can vary significantly in their response quality. In this paper, we investigate this problem of prompt fairness: specifically, the phrasing of a prompt by…
Latent Dirichlet Allocation (LDA) is a prominent generative probabilistic model used for uncovering abstract topics within document collections. In this paper, we explore the effectiveness of augmenting topic models with Large Language…
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…
This paper investigates the influence of cognitive biases on Large Language Models (LLMs) outputs. Cognitive biases, such as confirmation and availability biases, can distort user inputs through prompts, potentially leading to unfaithful…
Large language models (LLMs) inherit biases from their training data and alignment processes, influencing their responses in subtle ways. While many studies have examined these biases, little work has explored their robustness during…
Gradient-based deep-learning algorithms exhibit remarkable performance in practice, but it is not well-understood why they are able to generalize despite having more parameters than training examples. It is believed that implicit bias is a…
Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has…
As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of…
Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown that implicit stereotype-driven associations often persist. In…