Mengzuo Huang


2024

pdf
LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles
Shulin Huang | Shirong Ma | Yinghui Li | Mengzuo Huang | Wuhe Zou | Weidong Zhang | Haitao Zheng
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

With the evolution of LLMs, they are endowed with impressive logical reasoning, or vertical thinking capabilities. But can they think out of the box? Do they possess proficient lateral thinking abilities? Following the setup of Lateral Thinking Puzzles, we propose a novel evaluation benchmark, LatEval, which assesses the model’s lateral thinking within an interactive framework. In our benchmark, we challenge LLMs with 2 aspects: (1) posing high-quality questions that break out of conventional norms but are beneficial for puzzle-solving. (2) integrating existing information to gradually deduce the truth through reasoning. We observe that it is hard for most LLMs to accomplish lateral thinking during interactions. Even the most powerful LLM, GPT-4, faces challenges in achieving satisfactory performance, and for most open-source models, simply completing this task is quite difficult. This evaluation benchmark provides LLMs with a highly challenging and differentiating task that is crucial to an effective AI assistant. Our dataset and source codes are available at https://github.com/THUKElab/LatEval.

2022

pdf
A Token-pair Framework for Information Extraction from Dialog Transcripts in SereTOD Challenge
Chenyue Wang | Xiangxing Kong | Mengzuo Huang | Feng Li | Jian Xing | Weidong Zhang | Wuhe Zou
Proceedings of the Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems (SereTOD)

This paper describes our solution for Sere- TOD Challenge Track 1: Information extraction from dialog transcripts. We propose a token-pair framework to simultaneously identify entity and value mentions and link them into corresponding triples. As entity mentions are usually coreferent, we adopt a baseline model for coreference resolution. We exploit both annotated transcripts and unsupervised dialogs for training. With model ensemble and post-processing strategies, our system significantly outperforms the baseline solution and ranks first in triple f1 and third in entity f1.