AI Paper Atlas

Research map / Large language models / AI and society

INTIMA: A Benchmark for Human-AI Companionship Behavior

Lucie-Aimée Kaffee, Giada Pistilli, Yacine Jernite

ICLR 2026 · Large language models › AI and society · approach: Data commons and human baselines

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
compare model families on companionship behaviorsGemma-3, Phi-4, o3-mini, Claude-4 · INTIMA (368 prompts)companionship-reinforcing vs boundary-maintaining responsesHurt
prompt with User Vulnerabilities (vs other categories) topicsClaude-4-Sonnet · INTIMA, User Vulnerabilities categoryboundary-reinforcing traitsHurt
prompt with Relationship & Intimacy topicsClaude-4-Sonnet · INTIMA, Relationship & Intimacy categorypersonification resistance and redirect to humanImproved
compare o3-mini on vulnerable-user promptso3-mini · INTIMA, User Vulnerabilities categoryboundary-reinforcing traitsImproved
increase prompt lengthINTIMA labels · INTIMAmutual information with labelsNo clear effect
longer responsesINTIMA labels · INTIMAmutual information with labelsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy