Teng Shi — accepted AI-conference papers

2026

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering

Chenglei Shen, Zhongxiang Sun, Teng Shi, Xiao Zhang, Jun Xu

ICLR 2026poster

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness. Existing representation editing methods, by naively injecting…

Cited by 0 Source ↗Scholar ↗

2025

Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search

Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He +3

EMNLP 2025

Personalized search systems in e-commerce platforms increasingly involve user interactions with AI assistants, where users consult about products, usage scenarios, and more. Leveraging consultation to personalize search services is trending. Existing methods typically rely on semantic similarity to

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗