Publications

Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond

Published in EMNLP2023 Main Conference, 2024

This paper proposed a method to build a better tokenizer for downstream task.

Recommended citation: Liu, Siyang, Naihao Deng, Sahand Sabour, Yilin Jia, Minlie Huang and Rada Mihalcea. “Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond.” (2023). https://arxiv.org/abs/2310.05317

HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models

Published in EMNLP2023 Findings, 2024

This paper introduce HI-TOM, a Higher Order Theory of Mind benchmark for LLMs.

Recommended citation: He Yinghui, Yufan Wu, Yilin Jia, Rada Mihalcea, Yulong Chen and Naihao Deng. “HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models.” ArXiv abs/2310.16755 (2023): n. pag. https://arxiv.org/abs/2310.16755