Equipping machines with comprehensive knowledge of the world's entities and their
relationships has been a longstanding goal of AI. Over the last decade, large-scale …

Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational
facts from large corpora. The technique well suits many open-world natural language …

Modern summarization models generate highly fluent but often factually unreliable outputs.
This motivated a surge of metrics attempting to measure the factuality of automatically …

General purpose relation extractors, which can model arbitrary relations, are a core
aspiration in information extraction. Efforts have been made to build general purpose …

Existing visual question answering methods often suffer from cross-modal spurious
correlations and oversimplified event-level reasoning processes that fail to capture event …

Video grounding aims to localize a moment from an untrimmed video for a given textual
query. Existing approaches focus more on the alignment of visual and language stimuli with …

We introduce a method for improving the structural understanding abilities of language
models. Unlike previous approaches that finetune the models with task-specific …

Theory of Mind (ToM) $\unicode {x2014} $ the ability to reason about the mental states of
other people $\unicode {x2014} $ is a key element of our social intelligence. Yet, despite …

In the era of large language models (LLMs), hallucination (ie, the tendency to generate
factually incorrect content) poses great challenge to trustworthy and reliable deployment of …

Instant analysis of cybersecurity reports is a fundamental challenge for security experts as
an immeasurable amount of cyber information is generated on a daily basis, which …