Datasets·AI·aita_human_vs_qwen_3lens

AITA human vs Qwen

AITA: Human vs Qwen . PsyProxy quantitative evaluation. The excerpts reflect a range of interpersonal conflicts and emotional dilemmas, often revolving around themes of **communication**, **empathy**, and **boundaries**. Many texts explore the consequences of actions and decisions, highlighting the importance of considering the feelings of others while navigating complex relationships. The tone is often reflective and instructional, aiming to promote understanding and resolution rather than escalation. Recurring topics include **respect** for commitments, the impact of **trust** and betrayal in friendships, and the necessity of open dialogue in romantic partnerships. Additionally, there is a focus on **personal growth** and the challenges individuals face in balancing their own needs with those of others, emphasizing the need for **emotional intelligence** in various situations. [Summary on 50 random texts by ChatGPT 4o Mini].

Distribution of Human vs Qwen AITA-style writing
1
2
1,817 at floor2,000 at ceiling
3,817
items
763
holdout n
Human vs Qwen AITA-style writing
target
Binary
kind
15
systems compared
Criterion validity

Reported holdout systems from the verified card

Binary classification uses FVE as the task-primary metric. Secondary columns keep the companion metrics visible so binary, ordinal, regression, and multiclass cards are not compared through one flattened score.

Model-family mix
PsyProxy · 4Baseline · 11
SystemFamilyVariantFVEAUCF1Primary scale
psyproxyPsyProxy — Health Lens v0.9 · 1100d
PsyProxypermissive0.9841.0000.994
psyproxyPsyProxy — Technology Lens v0.5 · 800d
PsyProxypermissive0.9711.0000.994
psyproxyPsyProxy — Behavioral Sciences Lens v0.5 · 1000d
PsyProxypermissive0.9681.0000.994
psyproxyPsyProxy — Sociology Lens v0.5 · 1000d
PsyProxypermissive0.8460.9990.995
baselineIMDB movie reviews (ACL) binary · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews binary · via best lens
Baselinepermissive
baselineDisneyland TripAdvisor reviews binary · via best lens
Baselinepermissive
baselineLIAR fact-check statements ordinal · via best lens
Baselinepermissive
baselineDouban movie reviews (Chinese) ordinal · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews ordinal · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews continuous · via best lens
Baselinepermissive
baselineDisneyland TripAdvisor reviews continuous · via best lens
Baselinepermissive
baselineSentiment140 tweets binary · via best lens
Baselinepermissive
baselineDruglib drug reviews ordinal · via best lens
Baselinepermissive
baselineDruglib drug reviews regression · via best lens
Baselinepermissive