Deep neural networks exhibit vulnerability to word-level adversarial attacks in natural language processing. Most of these attack methods adopt synonymous substitutions to perturb original samples for crafting adversarial examples while attempting to maintain semantic consistency with the originals. Some of them claim that they could achieve over 90% attack success rate, thereby raising serious safety concerns. However, our investigation reveals that many purportedly successful adversarial examples are actually invalid due to significant changes in semantic meanings compared to their originals. Even when equipped with semantic constraints such as BERTScore, existing attack methods can generate up to 87.9% invalid adversarial examples. Building on this insight, we first curate a 13K dataset for adversarial validity evaluation with the help of GPT-4. Then, an open-source large language model is fine-tuned to offer an interpretable validity score for assessing the semantic consistency between original and adversarial examples. Finally, this validity score can serve as a guide for existing adversarial attack methods to generate valid adversarial examples. Comprehensive experiments demonstrate the effectiveness of our method in evaluating and refining the quality of adversarial examples.

Adversarial attacks on deep neural networks keep raising security concerns in natural language processing research. Existing defenses focus on improving the robustness of the victim model in the training stage. However, they often neglect to proactively mitigate adversarial attacks during inference. Towards this overlooked aspect, we propose a defense framework that aims to mitigate attacks by confusing attackers and correcting adversarial contexts that are caused by malicious perturbations. Our framework comprises three components: (1) a synonym-based transformation to randomly corrupt adversarial contexts in the word level, (2) a developed BERT defender to correct abnormal contexts in the representation level, and (3) a simple detection method to filter out adversarial examples, any of which can be flexibly combined. Additionally, our framework helps improve the robustness of the victim model during training. Extensive experiments demonstrate the effectiveness of our framework in defending against word-level adversarial attacks.

Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature. Recent research on advancing open-source smaller LMs by distilling knowledge from black-box LLMs has obtained promising results in the instruction-following ability. However, the reasoning ability which is more challenging to foster, is relatively rarely explored. In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability. In contrast to merely employing LLM as a data annotator, we exploit the potential of LLM as a reasoning teacher by building an interactive multi-round learning paradigm. This paradigm enables the student to expose its deficiencies to the black-box teacher who then can provide customized training data in return. Further, to exploit the reasoning potential of the smaller LM, we propose self-reflection learning to motivate the student to learn from self-made mistakes. The learning from self-reflection and LLM are all tailored to the student’s learning status, thanks to the seamless integration with the multi-round learning paradigm. Comprehensive experiments and analysis on mathematical and commonsense reasoning tasks demonstrate the effectiveness of our method. The code will be available at https://github.com/Raibows/Learn-to-Reason.

Emotion cause analysis (ECA) aims to extract emotion clauses and find the corresponding cause of the emotion. Existing methods adopt fine-tuning paradigm to solve certain types of ECA tasks. These task-specific methods have a deficiency of universality. And the relations among multiple objectives in one task are not explicitly modeled. Moreover, the relative position information introduced in most existing methods may make the model suffer from dataset bias. To address the first two problems, this paper proposes a universal prompt tuning method to solve different ECA tasks in the unified framework. As for the third problem, this paper designs a directional constraint module and a sequential learning module to ease the bias. Considering the commonalities among different tasks, this paper proposes a cross-task training method to further explore the capability of the model. The experimental results show that our method achieves competitive performance on the ECA datasets.