A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Large-scale computational comparison of two major Holocaust oral history collections shows both expected differences and significant overlaps in interview structure, yielding a replicable framework for archive analysis.
citing papers explorer
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
The Shape of Testimony: A Scalable Framework for Oral History Archive Comparison
Large-scale computational comparison of two major Holocaust oral history collections shows both expected differences and significant overlaps in interview structure, yielding a replicable framework for archive analysis.