Yunxiang Zhang

BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

A riddle is a question or statement with double or veiled meanings, followed by an unexpected answer. Solving riddle is a challenging task for both machine and human, testing the capability of understanding figurative, creative …

Enhancing Abstractive Dialogue Summarization with Internal Knowledge

2024

The task of dialogue summarization involves distilling a given dialogue into a concise and coherent summary. However, discrepancies in language styles between dialogues and summaries, scattered crucial information, incomplete utterances with ellipsis, and coreferences bring …

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training

2025 · arXiv (Cornell University)

Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification. Yet, these capabilities typically require resource-intensive post-training. We investigate whether such behaviors can be elicited in large models without any …