Jiaheng Zhang

Multi-scaled Topic Embedding for Text Classification

2022

Topic modeling and word embedding are commonly used techniques in natural language processing. However, word embedding lacks discriminating information of homonymy and polysemy as they typically assign a single vector for each word even if …

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning

2025 · arXiv (Cornell University)

Instruction fine-tuning (IFT) can increase the informativeness of large language models (LLMs), but may reduce their truthfulness. This trade-off arises because IFT steers LLMs to generate responses containing long-tail knowledge that was not well covered …