This paper investigates the group characteristics in multi-agent collaborative systems under adversarial attacks. Adversarial agents are tasked with generating counterfactual answers to a given collaborative problem, while collaborative agents normally interact with other agents to solve the given problem. To simulate real-world collaboration scenarios as closely as possible, we evaluate the collaborative system in three different collaboration scenarios and design three different communication strategies and different group structures. Furthermore, we explored several methods to mitigate adversarial attacks, all of which have been proven effective through our experiments. To quantify the robustness of collaborative systems against such attacks, a novel metric, System Defense Index (SDI), is introduced. Finally, we conducted an in-depth analysis from the perspective of group dynamics on how adversarial agents affect multi-agent collaborative systems, which reveals similarities between the agent collaboration process and human collaboration process. The code will be made available after publication.

Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks, WSD has achieved a great advancement in recent years. Reformulating WSD as a text span extraction task is an effective approach, which accepts a sentence context of an ambiguous word together with all definitions of its candidate senses simultaneously, and requires to extract the text span corresponding with the right sense. However, the approach merely depends on a short definition to learn sense representation, which neglects abundant semantic knowledge from related senses and leads to data-inefficient learning and suboptimal WSD performance. To address the limitations, we propose a novel WSD method with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (KELESC). Specifically, a knowledge-enhanced method is proposed to enrich semantic representation by incorporating additional examples and definitions of the related senses in WordNet. Then, in order to avoid the huge computing complexity induced by the additional information, a local self-attention mechanism is utilized to constrain attention to be local, which allows longer input texts without large-scale computing burdens. Extensive experimental results demonstrate that KELESC achieves better performance than baseline models on public benchmark datasets.