Yu-Che Tsai — accepted AI-conference papers

2026

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks

Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin

ICLR 2026poster

Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise an…

Cited by 0 Source ↗Scholar ↗

2026

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement

Yu-Che Tsai, Kuan-Yu Chen, Yuan-Chi Li, Yuan-Hao Chen, Ching-Yu Tsai, Shou-De Lin

ICLR 2026poster

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core gener- ative strengths. We introduce GIRCSE (Generative Iterative Refinement for Contrastive Sentence Embeddings), a novel framework th…

Cited by 0 Source ↗Scholar ↗