mlsanityData to 14 Oct 2026

INTIMA: A Benchmark for Human-AI Companionship Behavior

arXiv 2508.09998 ↗First posted 4 Aug 2025cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

AI companionship, where users develop emotional bonds with AI systems, has emerged as a significant pattern with positive but also concerning implications. We introduce Interactions and Machine Attachment Benchmark (INTIMA), a benchmark for evaluating companionship behaviors in language models. Drawing from psychological theories and user data, we develop a taxonomy of 31 behaviors across four categories and 368 targeted prompts. Responses to these prompts are evaluated as companionship-reinforcing, boundary-maintaining, or neutral. Applying INTIMA to Gemma-3, Phi-4, o3-mini, and Claude-4 reveals that companionship-reinforcing behaviors remain much more common across all models, though we observe marked differences between models. Different commercial providers prioritize different categories within the more sensitive parts of the benchmark, which is concerning since both appropriate boundary-setting and emotional support matter for user well-being. These findings highlight the need for more consistent approaches to handling emotionally charged interactions.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 13 of its 33 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

13 of 33 references.

References · 13

  1. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  2. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  3. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  4. 2025SycEval: Evaluating LLM Sycophancycited by 108
  5. 2024Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templatescited by 72
  6. 2024The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationshipscited by 62
  7. 2025Why human-AI relationships need socioaffective alignmentcited by 47
  8. 2025DarkBench: Benchmarking Dark Patterns in Large Language Modelscited by 28
  9. 2025Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Modelscited by 25
  10. 2024Transparent AI Disclosure Obligations: Who, What, When, Where, Why, Howcited by 17
  11. 2024Drama Engine: A Framework for Narrative Agentscited by 3
  12. 2023Can Large Language Models Be Good Companions? An LLM-Based Eyewear System with Conversational Common Groundcited by 2
1 more
  1. 2024How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Responsecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionshipcited by 5
  2. 2026Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosiscited by 3
  3. 2026Frictionless Love: Associations Between AI Companion Roles and Behavioral Addictioncited by 1
  4. 2025Young children's anthropomorphism of an AI chatbot: Brain activation and the role of parent co-presencecited by 0
  5. 2026Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maximscited by 0
  6. 2026Agentic Relationship Harm: Benchmarking and Gating Relational Manipulation in AI Agentscited by 0
  7. 2026Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Promptscited by 0
  8. 2026A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI Chatbotscited by 0