Inducing anxiety in large language models can induce bias

• URL: http://arxiv.org/abs/2304.11111v2
• Date: Tue, 15 Oct 2024 14:20:51 GMT
• Title: Inducing anxiety in large language models can induce bias
• Authors: Julian Coda-Forno, Kristin Witte, Akshay K. Jagadish, Marcel Binz, Zeynep Akata, Eric Schulz,
• Abstract summary: We focus on twelve established large language models (LLMs) and subject them to a questionnaire commonly used in psychiatry. Our results show that six of the latest LLMs respond robustly to the anxiety questionnaire, producing comparable anxiety scores to humans. Anxiety-induction not only influences LLMs' scores on an anxiety questionnaire but also influences their behavior in a previously-established benchmark measuring biases such as racism and ageism.
• Score: 47.85323153767388
• License:
• Abstract: Large language models (LLMs) are transforming research on machine learning while galvanizing public debates. Understanding not only when these models work well and succeed but also why they fail and misbehave is of great societal relevance. We propose to turn the lens of psychiatry, a framework used to describe and modify maladaptive behavior, to the outputs produced by these models. We focus on twelve established LLMs and subject them to a questionnaire commonly used in psychiatry. Our results show that six of the latest LLMs respond robustly to the anxiety questionnaire, producing comparable anxiety scores to humans. Moreover, the LLMs' responses can be predictably changed by using anxiety-inducing prompts. Anxiety-induction not only influences LLMs' scores on an anxiety questionnaire but also influences their behavior in a previously-established benchmark measuring biases such as racism and ageism. Importantly, greater anxiety-inducing text leads to stronger increases in biases, suggesting that how anxiously a prompt is communicated to large language models has a strong influence on their behavior in applied settings. These results demonstrate the usefulness of methods taken from psychiatry for studying the capable algorithms to which we increasingly delegate authority and autonomy.

Related papers

• StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly? [7.573284169975824]
  This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans. We developed a novel set of prompts, termed StressPrompt, designed to induce varying levels of stress. The findings suggest that LLMs, like humans, perform optimally under moderate stress, consistent with the Yerkes-Dodson law.
  arXiv  Detail & Related papers  (2024-09-14T08:32:31Z)
• Quantifying AI Psychology: A Psychometrics Benchmark for Large Language Models [57.518784855080334]
  Large Language Models (LLMs) have demonstrated exceptional task-solving capabilities, increasingly adopting roles akin to human-like assistants. This paper presents a framework for investigating psychology dimension in LLMs, including psychological identification, assessment dataset curation, and assessment with results validation. We introduce a comprehensive psychometrics benchmark for LLMs that covers six psychological dimensions: personality, values, emotion, theory of mind, motivation, and intelligence.
  arXiv  Detail & Related papers  (2024-06-25T16:09:08Z)
• Can AI Relate: Testing Large Language Model Response for Mental Health Support [23.97212082563385]
  Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. We develop an evaluation framework for determining whether LLM response is a viable and ethical path forward for the automation of mental health treatment.
  arXiv  Detail & Related papers  (2024-05-20T13:42:27Z)
• "I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust [51.542856739181474]
  We show how different natural language expressions of uncertainty impact participants' reliance, trust, and overall task performance. We find that first-person expressions decrease participants' confidence in the system and tendency to agree with the system's answers, while increasing participants' accuracy. Our findings suggest that using natural language expressions of uncertainty may be an effective approach for reducing overreliance on LLMs, but that the precise language used matters.
  arXiv  Detail & Related papers  (2024-05-01T16:43:55Z)
• Large Language Models are Capable of Offering Cognitive Reappraisal, if Guided [38.11184388388781]
  Large language models (LLMs) have offered new opportunities for emotional support. This work takes a first step by engaging with cognitive reappraisals. We conduct a first-of-its-kind expert evaluation of an LLM's zero-shot ability to generate cognitive reappraisal responses.
  arXiv  Detail & Related papers  (2024-04-01T17:56:30Z)
• HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy [25.908522131646258]
  We unveil the Helping and Empowering through Adaptive Language in Mental Enhancement (HealMe) model. This novel cognitive reframing therapy method effectively addresses deep-rooted negative thoughts and fosters rational, balanced perspectives. We adopt the first comprehensive and expertly crafted psychological evaluation metrics, specifically designed to rigorously assess the performance of cognitive reframing.
  arXiv  Detail & Related papers  (2024-02-26T09:10:34Z)
• Fine-Grained Self-Endorsement Improves Factuality and Reasoning [72.83651220132495]
  This work studies improving large language model (LLM) generations at inference time by mitigating fact-conflicting hallucinations. We propose a self-endorsement framework that leverages the fine-grained fact-level comparisons across multiple sampled responses.
  arXiv  Detail & Related papers  (2024-02-23T22:24:40Z)
• Do LLMs exhibit human-like response biases? A case study in survey design [66.1850490474361]
  We investigate the extent to which large language models (LLMs) reflect human response biases, if at all. We design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior.
  arXiv  Detail & Related papers  (2023-11-07T15:40:43Z)
• Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench [83.41621219298489]
  We propose a framework, PsychoBench, for evaluating diverse psychological aspects of Large Language Models (LLMs) PsychoBench classifies these scales into four distinct categories: personality traits, interpersonal relationships, motivational tests, and emotional abilities. We employ a jailbreak approach to bypass the safety alignment protocols and test the intrinsic natures of LLMs.
  arXiv  Detail & Related papers  (2023-10-02T17:46:09Z)
• The Confidence-Competence Gap in Large Language Models: A Cognitive Study [3.757390057317548]
  Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. We exploit these models with diverse sets of questionnaires and real-world scenarios. Our findings reveal intriguing instances where models demonstrate high confidence even when they answer incorrectly.
  arXiv  Detail & Related papers  (2023-09-28T03:50:09Z)

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.