Guanqun Yang

Guanqun Yang, Mirazul Haque, Qiaochu Song et al.

The recently proposed capability-based NLP testing allows model developers to test the functional capabilities of NLP models, revealing functional failures that cannot be detected by the traditional heldout mechanism. However, existing work on capability-based testing requires extensive manual efforts and domain expertise in creating the test cases. In this paper, we investigate a low-cost approach for the test case generation by leveraging the GPT-3 engine. We further propose to use a classifier to remove the invalid outputs from GPT-3 and expand the outputs into templates to generate more test cases. Our experiments show that TestAug has three advantages over the existing work on behavioral testing: (1) TestAug can find more bugs than existing work; (2) The test cases in TestAug are more diverse; and (3) TestAug largely saves the manual efforts in creating the test suites. The code and data for TestAug can be found at our project website (https://guanqun-yang.github.io/testaug/) and GitHub (https://github.com/guanqun-yang/testaug).

Jiangrui Zheng, Xueqing Liu, Guanqun Yang et al.

To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: do automated hate speech detectors conform to social media content policies? A platform's content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook's 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models' conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found in the attachment.

Sahil Wadhwa, Himanshu Kumar, Guanqun Yang et al.

Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step.

Guanqun Yang, Shay Dineen, Zhipeng Lin et al.

Public security vulnerability reports (e.g., CVE reports) play an important role in the maintenance of computer and network systems. Security companies and administrators rely on information from these reports to prioritize tasks on developing and deploying patches to their customers. Since these reports are unstructured texts, automatic information extraction (IE) can help scale up the processing by converting the unstructured reports to structured forms, e.g., software names and versions and vulnerability types. Existing works on automated IE for security vulnerability reports often rely on a large number of labeled training samples. However, creating massive labeled training set is both expensive and time consuming. In this work, for the first time, we propose to investigate this problem where only a small number of labeled training samples are available. In particular, we investigate the performance of fine-tuning several state-of-the-art pre-trained language models on our small training dataset. The results show that with pre-trained language models and carefully tuned hyperparameters, we have reached or slightly outperformed the state-of-the-art system on this task. Consistent with previous two-step process of first fine-tuning on main category and then transfer learning to others as in [7], if otherwise following our proposed approach, the number of required labeled samples substantially decrease in both stages: 90% reduction in fine-tuning from 5758 to 576,and 88.8% reduction in transfer learning with 64 labeled samples per category. Our experiments thus demonstrate the effectiveness of few-sample learning on NER for security vulnerability report. This result opens up multiple research opportunities for few-sample learning for security vulnerability reports, which is discussed in the paper. Code: https://github.com/guanqun-yang/FewVulnerability.