Xinyu Pi


2024

pdf bib
UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models
Xinyu Pi | Mingyuan Wu | Jize Jiang | Haozhen Zheng | Beitong Tian | ChengXiang Zhai | Klara Nahrstedt | Zhiting Hu
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Smaller-scale Vision-Language Models (VLMs) often claim to perform on par with larger models in general-domain visual grounding and question-answering benchmarks while offering advantages in computational efficiency and storage. However, their ability to handle rare objects, which fall into the long tail of data distributions, is less understood. To rigorously evaluate this aspect, we introduce the “Uncontextualized Uncommon Objects” (UOUO) benchmark. This benchmark focuses on systematically testing VLMs with both large and small parameter counts on rare and specialized objects. Our comprehensive analysis reveals that while smaller VLMs maintain competitive performance on common datasets, they significantly underperform on tasks involving uncommon objects. We also propose an advanced, scalable pipeline for data collection and cleaning, ensuring the UOUO benchmark provides high-quality, challenging instances. These findings highlight the need to consider long-tail distributions when assessing the true capabilities of VLMs. Code and project details for UOUO can be found at https://zoezheng126.github.io/UOUO-Website/.

2022

pdf bib
Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation
Xinyu Pi | Bing Wang | Yan Gao | Jiaqi Guo | Zhoujun Li | Jian-Guang Lou
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications. Previous studies along this line primarily focused on perturbations in the natural language question side, neglecting the variability of tables. Motivated by this, we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm to measure robustness of Text-to-SQL models. Following this proposition, we curate ADVETA, the first robustness evaluation benchmark featuring natural and realistic ATPs. All tested state-of-the-art models experience dramatic performance drops on ADVETA, revealing significant room of improvement. To defense against ATP, we build a systematic adversarial training example generation framework tailored for better contextualization of tabular data. Experiments show that our approach brings models best robustness improvement against ATP, while also substantially boost model robustness against NL-side perturbations. We will release ADVETA and code to facilitate future research.

pdf bib
Reasoning Like Program Executors
Xinyu Pi | Qian Liu | Bei Chen | Morteza Ziyadi | Zeqi Lin | Qiang Fu | Yan Gao | Jian-Guang Lou | Weizhu Chen
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Reasoning over natural language is a long-standing goal for the research community. However, studies have shown that existing language models are inadequate in reasoning. To address the issue, we present POET, a novel reasoning pre-training paradigm. Through pre-training language models with programs and their execution results, POET empowers language models to harvest the reasoning knowledge possessed by program executors via a data-driven approach. POET is conceptually simple and can be instantiated by different kinds of program executors. In this paper, we showcase two simple instances POET-Math and POET-Logic, in addition to a complex instance, POET-SQL. Experimental results on six benchmarks demonstrate that POET can significantly boost model performance in natural language reasoning, such as numerical reasoning, logical reasoning, and multi-hop reasoning. POET opens a new gate on reasoning-enhancement pre-training, and we hope our analysis would shed light on the future research of reasoning like program executors.