3 papers
cs.CL2026
Do LLM Debates Repeat Arguments Differently Across Languages?
Huiqian Lai
LLM debate is usually evaluated by final answers, yet transcripts reveal whether later turns develop new arguments or return to earlier claims in new wording. We study this process…
cs.HC2026
Fast-Food Intimacy: How Chinese Women Navigate Soul's AI Boyfriend
Huiqian Lai, EunJeong Cheon
On the Chinese social app Soul, millions of users - predominantly young women - are forming romantic connections with an AI boyfriend called "With-you." We conducted a qualitative…
cs.AI2026
Are LLMs More Skeptical of Entertainment News?
Huiqian Lai
Large language models (LLMs) are increasingly used for automated news credibility assessment, yet it remains unclear whether they apply even-handed standards across journalistic ge…