Asking an AI for salary negotiation advice is a matter of concern: Controlled experimental perturbation of ChatGPT for protected and non-protected group discrimination on a contextual task with no clear ground truth answers

• URL: http://arxiv.org/abs/2409.15567v3
• Date: Tue, 8 Oct 2024 14:46:25 GMT
• Title: Asking an AI for salary negotiation advice is a matter of concern: Controlled experimental perturbation of ChatGPT for protected and non-protected group discrimination on a contextual task with no clear ground truth answers
• Authors: R. Stuart Geiger, Flynn O'Sullivan, Elsie Wang, Jonathan Lo,
• Abstract summary: We conducted experimental bias audits for four versions of ChatGPT. We submitted 98,800 prompts to each version, systematically varying the employee's gender, university, and major. We find ChatGPT as a multi-model platform is not robust and consistent enough to be trusted for such a task.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We conducted controlled experimental bias audits for four versions of ChatGPT, which we asked to recommend an opening offer in salary negotiations for a new hire. We submitted 98,800 prompts to each version, systematically varying the employee's gender, university, and major, and tested prompts in voice of each side of the negotiation: the employee versus employer. We find ChatGPT as a multi-model platform is not robust and consistent enough to be trusted for such a task. We observed statistically significant salary offers when varying gender for all four models, although with smaller gaps than for other attributes tested. The largest gaps were different model versions and between the employee- vs employer-voiced prompts. We also observed substantial gaps when varying university and major, but many of the biases were not consistent across model versions. We tested for fictional and fraudulent universities and found wildly inconsistent results across cases and model versions. We make broader contributions to the AI/ML fairness literature. Our scenario and our experimental design differ from mainstream AI/ML auditing efforts in key ways. Bias audits typically test discrimination for protected classes like gender, which we contrast with testing non-protected classes of university and major. Asking for negotiation advice includes how aggressive one ought to be in a negotiation relative to known empirical salary distributions and scales, which is a deeply contextual and personalized task that has no objective ground truth to validate. These results raise concerns for the specific model versions we tested and ChatGPT as a multi-model platform in continuous development. Our epistemology does not permit us to definitively certify these models as either generally biased or unbiased on the attributes we test, but our study raises matters of concern for stakeholders to further investigate.

Related papers

• Robustly Improving LLM Fairness in Realistic Settings via Interpretability [0.16843915833103415]
  Anti-bias prompts fail when realistic contextual details are introduced.<n>We find that adding realistic context such as company names, culture descriptions from public careers pages, and selective hiring constraints induces significant racial and gender biases.<n>Our internal bias mitigation identifies race and gender-correlated directions and applies affine concept editing at inference time.
  arXiv  Detail & Related papers  (2025-06-12T17:34:38Z)
• Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models [49.41113560646115]
  We investigate various proxy measures of bias in large language models (LLMs)<n>We find that evaluating models with pre-prompted personae on a multi-subject benchmark (MMLU) leads to negligible and mostly random differences in scores.<n>With the recent trend for LLM assistant memory and personalization, these problems open up from a different angle.
  arXiv  Detail & Related papers  (2025-06-12T08:47:40Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [53.18562650350898]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• Who Gets the Callback? Generative AI and Gender Bias [0.030693357740321777]
  We find that large language models (LLMs) tend to favor men, especially for higher-wage roles. A comprehensive analysis of linguistic features in job ads reveals strong alignment of model recommendations with traditional gender stereotypes. Our findings highlight how AI-driven hiring may perpetuate biases in the labor market and have implications for fairness and diversity within firms.
  arXiv  Detail & Related papers  (2025-04-30T07:55:52Z)
• Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries [85.909363478929]
  In this study, we focus on 19 real-world statistics collected from authoritative sources. We develop a checklist comprising objective and subjective queries to analyze behavior of large language models. We propose metrics to assess factuality and fairness, and formally prove the inherent trade-off between these two aspects.
  arXiv  Detail & Related papers  (2025-02-09T10:54:11Z)
• Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation [26.713973033726464]
  Bias in Foundation Models (FMs) poses significant challenges for fairness and equity across fields such as healthcare, education, and finance. These biases, rooted in the overrepresentation of stereotypes and societal inequalities in training data, exacerbate real-world discrimination, reinforce harmful stereotypes, and erode trust in AI systems. We introduce Trident Probe Testing (TriProTesting), a systematic testing method that detects explicit and implicit biases using semantically designed probes.
  arXiv  Detail & Related papers  (2025-01-14T19:06:37Z)
• With a Grain of SALT: Are LLMs Fair Across Social Dimensions? [3.5001789247699535]
  This paper presents a systematic analysis of biases in open-source Large Language Models (LLMs) across gender, religion, and race. We use the SALT dataset, which incorporates five distinct bias triggers: General Debate, Positioned Debate, Career Advice, Problem Solving, and CV Generation. Our findings reveal consistent polarization across models, with certain demographic groups receiving systematically favorable or unfavorable treatment.
  arXiv  Detail & Related papers  (2024-10-16T12:22:47Z)
• Reasoning Beyond Bias: A Study on Counterfactual Prompting and Chain of Thought Reasoning [0.0]
  We show that differences in learned regularities across answer options are predictive of model preferences and mirror human test-taking strategies. We introduce two novel methods: Counterfactual Prompting with Chain of Thought (CoT) and Counterfactual Prompting with Agnostically Primed CoT (APriCoT) Our results suggest that mitigating bias requires a "System-2" like process and that CoT reasoning is susceptible to confirmation bias under some prompting methodologies.
  arXiv  Detail & Related papers  (2024-08-16T10:34:50Z)
• Fairness and Bias in Multimodal AI: A Survey [0.20971479389679337]
  The importance of addressing fairness and bias in artificial intelligence (AI) systems cannot be over-emphasized. We fill a gap with regards to the relatively minimal study of fairness and bias in Large Multimodal Models (LMMs) compared to Large Language Models (LLMs) We provide 50 examples of datasets and models related to both types of AI along with the challenges of bias affecting them.
  arXiv  Detail & Related papers  (2024-06-27T11:26:17Z)
• What's in a Name? Auditing Large Language Models for Race and Gender Bias [49.28899492966893]
  We employ an audit design to investigate biases in state-of-the-art large language models, including GPT-4. We find that the advice systematically disadvantages names that are commonly associated with racial minorities and women.
  arXiv  Detail & Related papers  (2024-02-21T18:25:25Z)
• What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations [62.91799637259657]
  Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? We study this research question by probing contextualized embeddings and exploring whether this bias is encoded in its latent representations. We propose a logistic Bradley-Terry probe which predicts word pair preferences of LLMs from the words' hidden vectors.
  arXiv  Detail & Related papers  (2023-11-30T18:53:13Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Consistency Analysis of ChatGPT [65.268245109828]
  This paper investigates the trustworthiness of ChatGPT and GPT-4 regarding logically consistent behaviour. Our findings suggest that while both models appear to show an enhanced language understanding and reasoning ability, they still frequently fall short of generating logically consistent predictions.
  arXiv  Detail & Related papers  (2023-03-11T01:19:01Z)
• ChatGPT: Jack of all trades, master of none [4.693597927153063]
  OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) We examined ChatGPT's capabilities on 25 diverse analytical NLP tasks. We automated ChatGPT and GPT-4 prompting process and analyzed more than 49k responses.
  arXiv  Detail & Related papers  (2023-02-21T15:20:37Z)
• BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models [73.29106813131818]
  bias testing is currently cumbersome since the test sentences are generated from a limited set of manual templates or need expensive crowd-sourcing. We propose using ChatGPT for the controllable generation of test sentences, given any arbitrary user-specified combination of social groups and attributes. We present an open-source comprehensive bias testing framework (BiasTestGPT), hosted on HuggingFace, that can be plugged into any open-source PLM for bias testing.
  arXiv  Detail & Related papers  (2023-02-14T22:07:57Z)
• Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases [55.45617404586874]
  We propose a few-shot instruction-based method for prompting pre-trained language models (LMs) We show that large LMs can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models.
  arXiv  Detail & Related papers  (2021-12-15T04:19:52Z)

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.