Yuan Tian

I work across linguistics, HCI, and social computing. My recent projects study AI companionship, bilingual ambiguity, multilingual interaction, and the social lives of language in both contemporary and historical settings.

Researcher trained in linguistics with corpus, field, and behavioral research experience. Recent work focuses on AI-mediated interaction, multilingual communication, and human-AI differences in language use and interpretation.

Education

• Stanford University — M.A. in East Asian Languages and Cultures (Chinese Linguistics) · Sep 2025 - Present
• Peking University — B.A. in Chinese Linguistics and Sociology (Dual Bachelor’s Degree) · Sep 2021 - Jul 2025

Research themes

• Harm reduction in AI companionship: Designing and evaluating conversational interventions for risky dependency, support-seeking, and attachment patterns.
• Pragmatics under ambiguity: Studying how humans and language models navigate modifier scope, bilingual ambiguity, and non-canonical interpretation.
• Language in social context: Connecting corpus analysis, fieldwork, and social theory to understand identity, stigma, and linguistic change.

Current directions

• LLM Peer Review and Revision: Critique Inflation and Advice–Reward Misalignment: Investigating how LLM-generated peer review shapes manuscript revision using rejected ICLR papers and multi-model reviewer, rewriter, and judge pipelines.
• AI-Assisted Scientific Reading: Borrowed Coherence and Independent Understanding: Investigating whether fluent, integrated AI explanations increase perceived understanding more than readers’ ability to independently reconstruct and evaluate scientific arguments.
• SafeCompanion: Evaluating Pushback/Friction as an Intervention for Harmful AI Interaction: Investigating mitigation strategies for high-risk AI companion interactions (e.g., emotional dependence) by evaluating user responses to varying levels of conversational friction.
• Bilingual Ambiguity Mental Models: Communication Strategies in Human vs. AI Interaction: Comparing communication strategies in human-human versus human-LLM interactions to understand how cognitive constraints shape strategy adoption in resolving bilingual ambiguity.