Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation

• URL: http://arxiv.org/abs/2407.08441v2
• Date: Thu, 13 Feb 2025 11:30:41 GMT
• Title: Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation
• Authors: Riccardo Cantini, Giada Cosenza, Alessio Orsino, Domenico Talia,
• Abstract summary: Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. These models are inherently prone to various biases stemming from their training data. This study explores the presence of these biases within the responses given by the most recent LLMs, analyzing the impact on their fairness and reliability.
• Score: 0.0
• License:
• Abstract: 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 data. These include selection, linguistic, and confirmation biases, along with common stereotypes related to gender, ethnicity, sexual orientation, religion, socioeconomic status, disability, and age. This study explores the presence of these biases within the responses given by the most recent LLMs, analyzing the impact on their fairness and reliability. We also investigate how known prompt engineering techniques can be exploited to effectively reveal hidden biases of LLMs, testing their adversarial robustness against jailbreak prompts specially crafted for bias elicitation. Extensive experiments are conducted using the most widespread LLMs at different scales, confirming that LLMs can still be manipulated to produce biased or inappropriate responses, despite their advanced capabilities and sophisticated alignment processes. Our findings underscore the importance of enhancing mitigation techniques to address these safety issues, toward a more sustainable and inclusive artificial intelligence.

Related papers

• LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language [29.327927413978003]
  This work reveals that many state-of-the-art LLMs are vulnerable to malicious requests hidden behind scientific language. Our experiments with GPT4o, GPT4o-mini, GPT-4, LLama3-405B-Instruct, Llama3-70B-Instruct, Cohere, Gemini models demonstrate that, the models' biases and toxicity substantially increase when prompted with requests that deliberately misinterpret social science and psychological studies as evidence supporting the benefits of stereotypical biases.
  arXiv  Detail & Related papers  (2025-01-23T20:20:20Z)
• Anchoring Bias in Large Language Models: An Experimental Study [5.229564709919574]
  Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence. This study delves into anchoring bias, a cognitive bias where initial information disproportionately influences judgment.
  arXiv  Detail & Related papers  (2024-12-09T15:45:03Z)
• CBEval: A framework for evaluating and interpreting cognitive biases in LLMs [1.4633779950109127]
  Large Language models exhibit notable gaps in their cognitive processes. As reflections of human-generated data, these models have the potential to inherit cognitive biases.
  arXiv  Detail & Related papers  (2024-12-04T05:53:28Z)
• The African Woman is Rhythmic and Soulful: An Investigation of Implicit Biases in LLM Open-ended Text Generation [3.9945212716333063]
  Implicit biases are significant because they influence the decisions made by Large Language Models (LLMs) Traditionally, explicit bias tests or embedding-based methods are employed to detect bias, but these approaches can overlook more nuanced, implicit forms of bias. We introduce two novel psychological-inspired methodologies to reveal and measure implicit biases through prompt-based and decision-making tasks.
  arXiv  Detail & Related papers  (2024-07-01T13:21:33Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities. If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information. To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Towards detecting unanticipated bias in Large Language Models [1.4589372436314496]
  Large Language Models (LLMs) have exhibited fairness issues similar to those in previous machine learning systems. This research focuses on analyzing and quantifying these biases in training data and their impact on the decisions of these models.
  arXiv  Detail & Related papers  (2024-04-03T11:25:20Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
  In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
  arXiv  Detail & Related papers  (2024-02-15T18:46:24Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.