Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs

Scott E. Friedman, Noam Benkler, Drisana Mosaphir, Jeffrey Rye, Sonja M. Schmer-Galunder +6 more
11/6/2024
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Exploring Large Language Models on Cross-Cultural Values in Connection with Training Methodology

86% match2024

Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches

85% match2024

Value Lens: Using Large Language Models to Understand Human Values

85% match2025

Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items

85% match2025

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models

84% match2026

ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models

84% match1 repo292024

Cite this paper

@article{friedman2024bottomup,
  title  = {Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs},
  author = {Scott E. Friedman and Noam Benkler and Drisana Mosaphir and Jeffrey Rye and Sonja M. Schmer-Galunder and Micah Goldwater and Matthew McLure and Ruta Wheelock and Jeremy Gottlieb and Robert P. Goldman and Christopher Miller},
  year   = {2024},
  eprint = {2411.05040},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.05040v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.05040.svg)](https://codeofpaper.com/paper/2411.05040)

Discussion