Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs
This work addresses the need for safety, accuracy, inclusion, and cultural fidelity in LLM adoption by enabling systematic analysis of values in corpora and LLMs, though it is incremental as it builds on existing value alignment research.
The paper tackled the problem of characterizing and managing socio-cultural values expressed by large language models (LLMs) by developing an automated approach to extract latent value propositions, assess value resonance and conflict, and evaluate pluralistic value alignment in textual data, resulting in a validated method applicable to both human-sourced and LLM-sourced texts.
Large language models (LLMs) generate diverse, situated, persuasive texts from a plurality of potential perspectives, influenced heavily by their prompts and training data. As part of LLM adoption, we seek to characterize - and ideally, manage - the socio-cultural values that they express, for reasons of safety, accuracy, inclusion, and cultural fidelity. We present a validated approach to automatically (1) extracting heterogeneous latent value propositions from texts, (2) assessing resonance and conflict of values with texts, and (3) combining these operations to characterize the pluralistic value alignment of human-sourced and LLM-sourced textual data.