Search papers, labs, and topics across Lattice.
This paper investigates biases in LLM-generated summaries of human life narratives, focusing on how LLMs' interpretations can skew the conclusions drawn from qualitative data. They introduce a summarization pipeline to identify biases related to race and gender in LLM-generated summaries. Their experiments reveal that LLMs exhibit biases that could lead to representational harm when interpreting life stories.
LLMs don't just summarize text; they subtly rewrite narratives through biased lenses, potentially distorting the very stories we're trying to understand.
Increasingly, studies are exploring using Large Language Models (LLMs) for accelerated or scaled qualitative analysis of text data. While we can compare LLM accuracy against human labels directly for deductive coding, or labeling text, it is more challenging to judge the ethics and effectiveness of using LLMs in abstractive methods such as inductive thematic analysis. We collaborate with psychologists to study the abstractive claims LLMs make about human life stories, asking, how does using an LLM as an interpreter of meaning affect the conclusions and perspectives of a study? We propose a summarization-based pipeline for surfacing biases in perspective-taking an LLM might employ in interpreting these life stories. We demonstrate that our pipeline can identify both race and gender bias with the potential for representational harm. Finally, we encourage the use of this analysis in future studies involving LLM-based interpretation of study participants'written text or transcribed speech to characterize a positionality portrait for the study.