PEFK (Prosocial and Effective Facilitation in Konversations)

Product or Programme · All products and programmes
Evidence · 4 claims (4 for) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 4 claims rest on one study

Description

A standardized, multi-domain compilation of online and oral discussion datasets created by Dimitris Tsirmpas and colleagues for benchmarking and analyzing facilitator interventions.

Components

• PEFK: a standardized multi-domain facilitation dataset: PEFK (Prosocial and Effective Facilitation in Konversations) is a standardized, multi-domain compilation of facilitation-related datasets listed by Korre et al. (2025), covering online forums and oral discussions such as debates and radio. The authors "standardizes metadata, metrics, and labeling schemes according to a simple, unified schema", making it suitable as a benchmark on facilitator interventions. It supports analysis under all three facilitation definitions, including escalation and toxicity fields, though the latter are not used in the study. (Dimitris Tsirmpas et al. (2026))

Claims

• Defining facilitation as speech produced by facilitators imposes a low performance ceiling on predictive facilitative models [+W]
• Humans are more certain when judging that facilitation is not needed than when judging it is [+W]
• LLMs are more intrusive and more consistent than humans, eager to view neutral discussions as opportunities for positive reinforcement [+W]
• ModernBert classifiers are more consistent than out-of-the-box LLMs at facilitation timing prediction, outperforming them in three of five datasets [+W]

Related Products and Programmes

-

Key Sources

• Dimitris Tsirmpas, Katerina Korre, John Pavlopoulos. (2026). To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussions. https://arxiv.org/abs/2607.28643

Page metadata

Field	Value
type	product
id	pefk-prosocial-and-effective-facilitation-in-konversations
title	PEFK (Prosocial and Effective Facilitation in Konversations)
description	A standardized, multi-domain compilation of online and oral discussion datasets created by Dimitris Tsirmpas and colleagues for benchmarking and analyzing facilitator interventions.
status	review
product_kind	dataset
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.