5 accepted papers
Many applications of Large Language Models (LLMs) require them to either simulate people or offer personalized functionality, making the demographic representativeness of LLMs crucial for equitable utility. At the same time, we know little about the extent to which these models actually reflect the…
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark for evaluating representational similarity measures based on well-defined groun…
Persona prompting is increasingly used in large language models (LLMs) to simulate views of various sociodemographic groups. However, how a persona prompt is formulated can significantly affect outcomes, raising concerns about the fidelity of such simulations. Using five open-source LLMs, we systema
Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incomplete. We introduce local contrastive editing that enables the localization and editing of a subset of weights in a target…
Adding interpretability to word embeddings represents an area of active research in textrepresentation. Recent work has explored the potential of embedding words via so-called polardimensions (e.g. good vs. bad, correct vs. wrong). Examples of such recent approachesinclude SemAxis, POLAR, FrameAxis,…