CBEval: A framework for evaluating and interpreting cognitive biases in LLMs
read the original abstract
Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally, as reflections of human-generated data, these models have the potential to inherit cognitive biases, raising concerns about their reasoning and decision making capabilities. In this paper we present a framework to interpret, understand and provide insights into a host of cognitive biases in LLMs. Conducting our research on frontier language models we're able to elucidate reasoning limitations and biases, and provide reasoning behind these biases by constructing influence graphs that identify phrases and words most responsible for biases manifested in LLMs. We further investigate biases such as round number bias and cognitive bias barrier revealed when noting framing effect in language models.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
AMEL: Accumulated Message Effects on LLM Judgments
LLMs exhibit an accumulated message effect where conversation history saturated with positive or negative evaluations biases subsequent judgments, with larger shifts on uncertain items, a negativity asymmetry, and no ...
-
AMEL: Accumulated Message Effects on LLM Judgments
LLMs exhibit an accumulated message effect where conversation history polarity biases subsequent judgments, stronger for high-entropy items, independent of context length, and with a negativity bias.
-
Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models
LLMs exhibit quality-dependent order biases and name biases in pairwise comparisons that can cause selection of inferior options, demonstrated across resume and color tasks with a new classification of preferences as ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.