Lin Ai

Machine Reading Comprehension (MRC) poses a significant challenge in the field of Natural Language Processing (NLP). While mainstream MRC methods predominantly leverage extractive strategies using encoder-only models such as BERT, generative approaches face the issue of out-of-control generation – a critical problem where answers generated are often incorrect, irrelevant, or unfaithful to the source text. To address these limitations in generative models for MRC, we introduce the Question-Attended Span Extraction (QASE) module. Integrated during the fine-tuning phase of pre-trained generative language models (PLMs), QASE significantly enhances their performance, allowing them to surpass the extractive capabilities of advanced Large Language Models (LLMs) such as GPT-4. Notably, these gains in performance do not come with an increase in computational demands. The efficacy of the QASE module has been rigorously tested across various datasets, consistently achieving or even surpassing state-of-the-art (SOTA) results.

The proliferation of Large Language Models (LLMs) poses challenges in detecting and mitigating digital deception, as these models can emulate human conversational patterns and facilitate chat-based social engineering (CSE) attacks. This study investigates the dual capabilities of LLMs as both facilitators and defenders against CSE threats. We develop a novel dataset, SEConvo, simulating CSE scenarios in academic and recruitment contexts, and designed to examine how LLMs can be exploited in these situations. Our findings reveal that, while off-the-shelf LLMs generate high-quality CSE content, their detection capabilities are suboptimal, leading to increased operational costs for defense. In response, we propose ConvoSentinel, a modular defense pipeline that improves detection at both the message and the conversation levels, offering enhanced adaptability and cost-effectiveness. The retrieval-augmented module in ConvoSentinel identifies malicious intent by comparing messages to a database of similar conversations, enhancing CSE detection at all stages. Our study highlights the need for advanced strategies to leverage LLMs in cybersecurity.

Open Information Extraction (OpenIE) represents a crucial NLP task aimed at deriving structured information from unstructured text, unrestricted by relation type or domain. This survey paper provides an overview of OpenIE technologies spanning from 2007 to 2024, emphasizing a chronological perspective absent in prior surveys. It examines the evolution of task settings in OpenIE to align with the advances in recent technologies. The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework. Additionally, it highlights prevalent datasets and evaluation metrics currently in use. Building on this extensive review, the paper outlines potential future directions in terms of datasets, information sources, output formats, methodologies, and evaluation metrics.

This paper introduces TweetIntent@Crisis, a novel Twitter dataset centered on the Russia-Ukraine crisis. Comprising over 17K tweets from government-affiliated accounts of both nations, the dataset is meticulously annotated to identify underlying intents and detailed intent-related information. Our analysis demonstrates the dataset’s capability in revealing fine-grained intents and nuanced narratives within the tweets from both parties involved in the crisis. We aim for TweetIntent@Crisis to provide the research community with a valuable tool for understanding and analyzing granular media narratives and their impact in this geopolitical conflict.

While COVID-19 has affected most of the world, attempts to control it have been difficult due to the lack of trustworthy information about the virus’s origin, severity, effective treatments, and prevention measures. To address this, we have collected RTCas-COVID-19, a large corpus of 35M COVID-19 tweets from 2020, and weak-labeled 2M with a semi-supervised approach. We have also developed an inductive framework, RTCS-HGT (Retweet Cascade Subgraph Sampling Heterogeneous Graph Transformer), which achieves 0.918 test accuracy on tweet trustworthiness classification on our dataset and improves training time by 93%.