相关论文: Attacking Open-domain Question Answering by Inject…

With a lot of work about context-free question answering systems, there is an emerging trend of conversational question answering models in the natural language processing field. Thanks to the recently collected datasets, including QuAC and…

Document Visual Question Answering (DocVQA) enables end-to-end reasoning grounded on information present in a document input. While recent models have shown impressive capabilities, they remain vulnerable to adversarial attacks. In this…

Research in combating misinformation reports many negative results: facts may not change minds, especially if they come from sources that are not trusted. Individuals can disregard and justify lies told by trusted sources. This problem is…

Disinformation campaigns can distort public perception and destabilize institutions. Understanding how different populations respond to information is crucial for designing effective interventions, yet real-world experimentation is…

Misinformation and disinformation pose significant risks globally, with the Arab region facing unique vulnerabilities due to geopolitical instabilities, linguistic diversity, and cultural nuances. We explore these challenges through the key…

Automated disinformation generation is often listed as an important risk associated with large language models (LLMs). The theoretical ability to flood the information space with disinformation content might have dramatic consequences for…

With the rapid development of knowledge bases(KBs),question answering(QA)based on KBs has become a hot research issue. In this paper,we propose two frameworks(i.e.,pipeline framework,an end-to-end framework)to focus answering…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

The recent success in language generation capabilities of large language models (LLMs), such as GPT, Bard, Llama etc., can potentially lead to concerns about their possible misuse in inducing mass agitation and communal hatred via…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

The rise in online misinformation in recent years threatens democracies by distorting authentic public discourse and causing confusion, fear, and even, in extreme cases, violence. There is a need to understand the spread of false content…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

An abundance of literature has shown that the injection of noise into complex socio-economic systems can improve their resilience. This study aims to understand whether the same applies in the context of information diffusion in social…

AI, especially Large Language Models (LLMs) like ChatGPT, have rapidly developed and gained widespread adoption in the past five years, shifting user preference from traditional search engines. However, the generative nature of LLMs raises…

While numerous methods have been proposed as defenses against adversarial examples in question answering (QA), these techniques are often model specific, require retraining of the model, and give only marginal improvements in performance…

Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, finance, and legal contexts. Given a query, RAG retrieves relevant…

Causality has been recently introduced in databases, to model, characterize, and possibly compute causes for query answers. Connections between QA-causality and consistency-based diagnosis and database repairs (wrt. integrity constraint…

This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. We focus on informative conversations, including business emails, panel discussions, and work channels. Unlike open-domain…

With the rapid increase in access to internet and the subsequent growth in the population of online social media users, the quality of information posted, disseminated and consumed via these platforms is an issue of growing concern. A large…

Question Answering (QA) is not a new research field in Natural Language Processing (NLP). However in recent years, QA has been a subject of growing study. Nowadays, most of the QA systems have a similar pipelined architecture and each…