Related papers: MOKA: Moral Knowledge Augmentation for Moral Event…
Audio LLMs have shown a strong ability to understand audio samples, yet their reliability in complex acoustic scenes remains under-explored. Unlike prior work limited to small scale or less controlled query construction, we present a…
Political polarization in the US is on the rise. This polarization negatively affects the public sphere by contributing to the creation of ideological echo chambers. In this paper, we focus on addressing one of the factors that contributes…
LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple…
Knowledge editing aims to adjust the knowledge within large language models (LLMs) to prevent their responses from becoming obsolete or inaccurate. However, existing works on knowledge editing are primarily conducted in a single language,…
Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a…
Large language models (LLMs) generate diverse, situated, persuasive texts from a plurality of potential perspectives, influenced heavily by their prompts and training data. As part of LLM adoption, we seek to characterize - and ideally,…
As an essential component of human cognition, cause-effect relations appear frequently in text, and curating cause-effect relations from text helps in building causal networks for predictive tasks. Existing causality extraction techniques…
The widespread dissemination of multimodal content on social media has made misinformation detection increasingly challenging, as misleading narratives often arise not only from textual or visual content alone, but also from semantic…
Polarization, declining trust, and wavering support for democratic norms are pressing threats to U.S. democracy. Exposure to verified and quality news may lower individual susceptibility to these threats and make citizens more resilient to…
The ability to track large-scale events as they happen is essential for understanding them and coordinating reactions in an appropriate and timely manner. This is true, for example, in emergency management and decision-making support, where…
Teaching morals is one of the most important purposes of storytelling. An essential ability for understanding and writing moral stories is bridging story plots and implied morals. Its challenges mainly lie in: (1) grasping knowledge about…
In this work, we investigate the effectiveness of injecting external knowledge to a large language model (LLM) to identify semantic plausibility of simple events. Specifically, we enhance the LLM with fine-grained entity types, event types…
Free-text rationales play a pivotal role in explainable NLP, bridging the knowledge and reasoning gaps behind a model's decision-making. However, due to the diversity of potential reasoning paths and a corresponding lack of definitive…
Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction. On the…
As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved…
Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce the available…
Dark humor often relies on subtle cultural nuances and implicit cues that require contextual reasoning to interpret, posing safety challenges that current static benchmarks fail to capture. To address this, we introduce a novel multimodal,…
We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of…
How do Large Language Models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In contrast to prior work using deterministic ground truth…
The rapid spread of information through mobile devices and media has led to the widespread of false or deceptive news, causing significant concerns in society. Among different types of misinformation, image repurposing, also known as…