SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

Hugging Face Daily Papers Papers

Summary

SoCRATES introduces a realistic multi-domain benchmark for evaluating proactive LLM mediators, showing that top models resolve only about one-third of the consensus gap in conflict resolution.

Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary mainly strategic posture, and score every turn against every topic, introducing off-topic noise. We introduce SoCRATES, a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It constructs scenarios from real conflicts through an agentic pipeline across eight domains, probes five socio-cognitive adaptation axes (strategic posture, party composition, history length, emotional reactivity, and cultural identity), and scores each topic only on the turns that advance it via a topic-localized evaluator. The evaluator reaches 0.82 alignment with human experts, more than doubling a per-turn baseline. Benchmarking eight frontier LLMs, we find that even the strongest mediator closes only about a third of the unmediated consensus gap under diverse and realistic testbeds, with performance varying sharply by socio-cognitive axis, highlighting that progress lies in social adaptation to diverse conditions.
Original Article
View Cached Full Text

Cached at: 06/08/26, 11:15 AM

Paper page - SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

Source: https://huggingface.co/papers/2606.05563

Abstract

SoCRATES presents a realistic multi-domain benchmark for evaluating proactive LLM mediators across various socio-cognitive adaptation axes, demonstrating that even top-performing models only resolve about one-third of the consensus gap in conflict resolution.

EvaluatingLLM mediatorsremains challenging, as mediation unfolds as areal-time trajectoryshaped by disputants’ shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary mainly strategic posture, and score every turn against every topic, introducing off-topic noise. We introduce SoCRATES, a benchmark for evaluating proactiveLLM mediatorsin realistic,multi-domain testbeds. It constructs scenarios from real conflicts through anagentic pipelineacross eight domains, probes fivesocio-cognitive adaptationaxes (strategic posture, party composition, history length, emotional reactivity, and cultural identity), and scores each topic only on the turns that advance it via atopic-localized evaluator. The evaluator reaches 0.82 alignment with human experts, more than doubling a per-turn baseline. Benchmarking eight frontier LLMs, we find that even the strongest mediator closes only about a third of the unmediatedconsensus gapunder diverse and realistic testbeds, with performance varying sharply by socio-cognitive axis, highlighting that progress lies in social adaptation to diverse conditions.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2606\.05563

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.05563 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.05563 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.05563 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Hugging Face Daily Papers

Counsel is the first public dataset of human meta-evaluations of LLM critiques for agentic tasks, designed to improve the calibration and reliability of automated evaluation methods.