AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sakhawat, Adib, Sadab, Fardeen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917279599427584
author Sakhawat, Adib
Sadab, Fardeen
author_facet Sakhawat, Adib
Sadab, Fardeen
contents Evaluating the social intelligence of Large Language Models (LLMs) increasingly requires moving beyond static text generation toward dynamic, adversarial interaction. We introduce the Adversarial Resource Extraction Game (AREG), a benchmark that operationalizes persuasion and resistance as a multi-turn, zero-sum negotiation over financial resources. Using a round-robin tournament across frontier models, AREG enables joint evaluation of offensive (persuasion) and defensive (resistance) capabilities within a single interactional framework. Our analysis provides evidence that these capabilities are weakly correlated ($ρ= 0.33$) and empirically dissociated: strong persuasive performance does not reliably predict strong resistance, and vice versa. Across all evaluated models, resistance scores exceed persuasion scores, indicating a systematic defensive advantage in adversarial dialogue settings. Further linguistic analysis suggests that interaction structure plays a central role in these outcomes. Incremental commitment-seeking strategies are associated with higher extraction success, while verification-seeking responses are more prevalent in successful defenses than explicit refusal. Together, these findings indicate that social influence in LLMs is not a monolithic capability and that evaluation frameworks focusing on persuasion alone may overlook asymmetric behavioral vulnerabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16639
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models
Sakhawat, Adib
Sadab, Fardeen
Computation and Language
Evaluating the social intelligence of Large Language Models (LLMs) increasingly requires moving beyond static text generation toward dynamic, adversarial interaction. We introduce the Adversarial Resource Extraction Game (AREG), a benchmark that operationalizes persuasion and resistance as a multi-turn, zero-sum negotiation over financial resources. Using a round-robin tournament across frontier models, AREG enables joint evaluation of offensive (persuasion) and defensive (resistance) capabilities within a single interactional framework. Our analysis provides evidence that these capabilities are weakly correlated ($ρ= 0.33$) and empirically dissociated: strong persuasive performance does not reliably predict strong resistance, and vice versa. Across all evaluated models, resistance scores exceed persuasion scores, indicating a systematic defensive advantage in adversarial dialogue settings. Further linguistic analysis suggests that interaction structure plays a central role in these outcomes. Incremental commitment-seeking strategies are associated with higher extraction success, while verification-seeking responses are more prevalent in successful defenses than explicit refusal. Together, these findings indicate that social influence in LLMs is not a monolithic capability and that evaluation frameworks focusing on persuasion alone may overlook asymmetric behavioral vulnerabilities.
title AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2602.16639