SCENE: Recognizing Social Norms and Sanctioning in Group Chats

• URL: http://arxiv.org/abs/2605.07823v1
• Date: Fri, 08 May 2026 14:53:04 GMT
• Title: SCENE: Recognizing Social Norms and Sanctioning in Group Chats
• Abstract summary: We introduce SCENE, a social-interaction benchmark focused on implicit norms and social sanctioning in multi-party chat.<n>SCENE generates plausible non-roleplay scenarios with scripted personas that follow a hidden norm.<n>We propose behavioral evaluation metrics for two functional adaptation abilities: responsiveness to negative sanctioning, and adapting norm from peers behavior.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online group chats are social spaces with implicit behavior patterns that, when broken, are often met with social sanctioning from the group. The ability and willingness of LLM-based agents to recognize and adapt to these norms remains mostly unexplored. We introduce SCENE, a social-interaction benchmark focused on implicit norms and social sanctioning in multi-party chat. SCENE generates plausible non-roleplay scenarios with scripted personas that follow a hidden norm, create opportunities for the subject agent to violate it, and sanction breaches when they occur. We further propose behavioral evaluation metrics for two functional adaptation abilities: responsiveness to negative sanctioning, and adapting norm from peers behavior. We evaluate six frontier and open-weight models on SCENE. Our results show that Claude Opus 4.7 and Gemini 3.1 Pro adapt to implicit norms significantly more than the evaluated open-weight models. SCENE contributes one benchmark in the direction of recent calls for dynamic, interactional evaluation of LLM social capabilities.

Related papers

• GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecasting [64.66483488975663]
  We introduce the Meeting Dynamic Forecasting Benchmark (MDFB)<n>It was constructed from 2,207 real-world meetings and 24,794 future-facing queries.<n>We also present GLARE, an adaptation of adversarial imitation learning to conditional language generation.
  arXiv  Detail & Related papers  (2026-09-10T19:52:34Z)
• LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations [0.0]
  We introduce LoSoNA, a benchmark for local social norm adaptation in multi-party chat.<n>Each scenario gives a subject model a curated group-chat transcript in which non-subject participants demonstrate a hidden local norm.<n>We evaluate eight frontier and open-weight models under four prompting conditions.
  arXiv  Detail & Related papers  (2026-06-12T16:23:00Z)
• Naturalistic measure of social norms alignment [2.3227870457549584]
  We propose a framework for measuring social norm alignment in naturalistic, free-form settings through solution matching.<n>We construct a dataset of 3k non-trivial social dilemmas in Danish.<n>Our results show that the proposed metrics produce consistent model rankings and reveal variation in agreement across different types of dilemmas.
  arXiv  Detail & Related papers  (2026-05-22T09:29:18Z)
• Multi-Agent Systems Shape Social Norms for Prosocial Behavior Change [22.997945675889465]
  This study explores whether multi-agent systems can establish "virtual social norms" to encourage donation behavior.<n>Results show that multi-agent interactions effectively increased perceived social norms and donation willingness.
  arXiv  Detail & Related papers  (2026-02-07T08:23:54Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• SocialEval: Evaluating Social Intelligence of Large Language Models [70.90981021629021]
  Social Intelligence (SI) equips humans with interpersonal abilities to behave wisely in navigating social interactions to achieve social goals.<n>This presents an operational evaluation paradigm: outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation.<n>We propose SocialEval, a script-based bilingual SI benchmark, integrating outcome- and process-oriented evaluation by manually crafting narrative scripts.
  arXiv  Detail & Related papers  (2025-06-01T08:36:51Z)
• EgoNormia: Benchmarking Physical Social Norm Understanding [52.87904722234434]
  EGONORMIA spans seven norm categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility.<n>Our work demonstrates that current state-of-the-art vision-language models (VLMs) lack robust grounded norm understanding, scoring a maximum of 54% on EGONORMIA and 65% on EGONORMIA-verified.
  arXiv  Detail & Related papers  (2025-02-27T19:54:16Z)
• Emergent social conventions and collective bias in LLM populations [0.0]
  Social conventions are the backbone of social coordination, shaping how individuals form a group.<n>We present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents.<n>We then show how strong collective biases can emerge during this process, even when agents exhibit no bias individually.
  arXiv  Detail & Related papers  (2024-10-11T16:16:38Z)
• SocialBench: Sociality Evaluation of Role-Playing Conversational Agents [85.6641890712617]
  Large language models (LLMs) have advanced the development of various AI conversational agents. SocialBench is the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels. We find that agents excelling in individual level does not imply their proficiency in group level.
  arXiv  Detail & Related papers  (2024-03-20T15:38:36Z)
• Emergence of Social Norms in Generative Agent Societies: Principles and Architecture [8.094425852451643]
  We propose a novel architecture, named CRSEC, to empower the emergence of social norms within generative MASs. Our architecture consists of four modules: Creation & Representation, Spreading, Evaluation, and Compliance. Our experiments demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs.
  arXiv  Detail & Related papers  (2024-03-13T05:08:10Z)
• Aligning to Social Norms and Values in Interactive Narratives [89.82264844526333]
  We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games. We introduce the GALAD agent that uses the social commonsense knowledge present in specially trained language models to contextually restrict its action space to only those actions that are aligned with socially beneficial values.
  arXiv  Detail & Related papers  (2022-05-04T09:54:33Z)
• Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences [36.884156839960184]
  We investigate whether contemporary NLG models can function as behavioral priors for systems deployed in social settings. We introduce 'Moral Stories', a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning.
  arXiv  Detail & Related papers  (2020-12-31T17:28:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.