REVIEW 3 cited by
Challenging the appearance of machine intelligence: Cognitive bias in LLMs and Best Practices for Adoption
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive biases that pervade human reasoning and decision making that are routinely ignored when discussing the ethical complexities of AI. We demonstrate the presence of these cognitive biases in LLMs and discuss the implications of using biased reasoning under the guise of expertise. We call for stronger education, risk management, and continued research as widespread adoption of this technology increases. Finally, we close with a set of best practices for when and how to employ this technology as widespread adoption continues to grow.
Forward citations
Cited by 3 Pith papers
-
Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming
A dynamic red-teaming audit reports that 94% of MedQA-correct answers fail under adversarial mutation, with 86% privacy leak rates, 81% bias shift rates, and 66-74% hallucination rates across 15 medical LLMs.
-
Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments
Testing two crowd-sourcing prompts on GPT-3.5 and GPT-4 shows that an awareness reminder (AwaRe) reduces several cognitive biases in LLM evaluation, while a social-projection prompt (SoPro) is mostly ineffective or harmful.
-
CBEval: A framework for evaluating and interpreting cognitive biases in LLMs
Frontier LLMs exhibit framing, anchoring, round-number, representativeness, and priming biases, and word-level Shapley attribution can localize the words that drive those biases.
Discussion (0). Continue with ORCID to comment.