Xiaofeng Shi

PALI at SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts

2022 · Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper describes our system used in the SemEval-2022 Task 7(Roth et al.): Identifying Plausible Clarifications of Implicit and Underspecified Phrases. Semeval Task7 is an more complex cloze task, different than normal cloze task, only …

SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation

2025 · arXiv (Cornell University)

The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address these limitations, we introduce SciSage, …