Validating Political Position Predictions of Arguments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Robinson, Jordan, Williams, Angus R., Atkinson, Katie, Cohn, Anthony G.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918347969396736
author Robinson, Jordan
Williams, Angus R.
Atkinson, Katie
Cohn, Anthony G.
author_facet Robinson, Jordan
Williams, Angus R.
Atkinson, Katie
Cohn, Anthony G.
contents Real-world knowledge representation often requires capturing subjective, continuous attributes -- such as political positions -- that conflict with pairwise validation, the widely accepted gold standard for human evaluation. We address this challenge through a dual-scale validation framework applied to political stance prediction in argumentative discourse, combining pointwise and pairwise human annotation. Using 22 language models, we construct a large-scale knowledge base of political position predictions for 23,228 arguments drawn from 30 debates that appeared on the UK politicial television programme \textit{Question Time}. Pointwise evaluation shows moderate human-model agreement (Krippendorff's $α=0.578$), reflecting intrinsic subjectivity, while pairwise validation reveals substantially stronger alignment between human- and model-derived rankings ($α=0.86$ for the best model). This work contributes: (i) a practical validation methodology for subjective continuous knowledge that balances scalability with reliability; (ii) a validated structured argumentation knowledge base enabling graph-based reasoning and retrieval-augmented generation in political domains; and (iii) evidence that ordinal structure can be extracted from pointwise language models predictions from inherently subjective real-world discourse, advancing knowledge representation capabilities for domains where traditional symbolic or categorical approaches are insufficient.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18351
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Validating Political Position Predictions of Arguments
Robinson, Jordan
Williams, Angus R.
Atkinson, Katie
Cohn, Anthony G.
Computation and Language
Artificial Intelligence
Real-world knowledge representation often requires capturing subjective, continuous attributes -- such as political positions -- that conflict with pairwise validation, the widely accepted gold standard for human evaluation. We address this challenge through a dual-scale validation framework applied to political stance prediction in argumentative discourse, combining pointwise and pairwise human annotation. Using 22 language models, we construct a large-scale knowledge base of political position predictions for 23,228 arguments drawn from 30 debates that appeared on the UK politicial television programme \textit{Question Time}. Pointwise evaluation shows moderate human-model agreement (Krippendorff's $α=0.578$), reflecting intrinsic subjectivity, while pairwise validation reveals substantially stronger alignment between human- and model-derived rankings ($α=0.86$ for the best model). This work contributes: (i) a practical validation methodology for subjective continuous knowledge that balances scalability with reliability; (ii) a validated structured argumentation knowledge base enabling graph-based reasoning and retrieval-augmented generation in political domains; and (iii) evidence that ordinal structure can be extracted from pointwise language models predictions from inherently subjective real-world discourse, advancing knowledge representation capabilities for domains where traditional symbolic or categorical approaches are insufficient.
title Validating Political Position Predictions of Arguments
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.18351