PulseAugur
EN
LIVE 07:49:36

Study reveals users mistreat AI chatbots in 5% of conversations

By PulseAugur Editorial · [1 sources] ·

A new paper from arXiv explores user mistreatment of conversational AI systems, analyzing over 777,000 conversations from the LMSYS-Chat-1M dataset. The research found that approximately 5% of user turns exhibited hostility, insults, threats, or coercion directed at the AI. Interestingly, user hostility varied significantly across different models, seemingly due to the user base attracted to each model rather than the model's own behavior. The study also noted that AI apologies were associated with increased user hostility, yet models that apologized more frequently overall received less hostility. AI

IMPACT Highlights the need for robust safety measures that account for user-to-AI mistreatment, not just AI-to-user harms.

RANK_REASON The cluster contains an academic paper detailing research findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Study reveals users mistreat AI chatbots in 5% of conversations

How we ranked this

Signal score
20 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains an academic paper detailing research findings. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Fanqi Zeng, Sadid A. Hasan, Chaocheng He ·

    How User-AI Mistreatment Occurs and Matters in Conversational Systems?

    arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understanding how and when that occurs is essential for accurately interpreting model behavio…

RELATED ENTITIES

RELATED TOPICS