Add to ORKGDocument-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report may not be explicitly stated in one place, but nevertheless can be inferred from parts of the report's text. However, these models can easily learn spurious correlations between labels and irrelevant information. This work studies how to ensure that these models make correct inferences from complex text and make those inferences in an auditable way: beyond just being right, are these models "right for the right reasons?" We experiment with post-hoc evidence extraction in a predict-select-verify...
Drawing conclusions about real-world relationships of cause and effect from data collected without r...
The scientific claim verification task requires an NLP system to label scientific documents which Su...
While Transformer language models (LMs) are state-of-the-art for information extraction, long text i...
The emergence of Large Language Models (LLMs) has boosted performance and possibilities in various N...
Text-mining algorithms make mistakes in extracting facts from natural-language texts. In biomedical ...
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may con...
Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truth...
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread ...
KGCleaner is a framework to identify and correct errors in data produced and delivered by an informa...
A central question in natural language understanding (NLU) research is whether high performance demo...
While deep neural network models offer unmatched classification performance, they are prone to learn...
Automated fact-checking (AFC) systems exist to combat disinformation, however their complexity usual...
Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-...
Text-mining algorithms make mistakes in extracting facts from natural-language texts. In biomedical ...
A key component of fact verification is thevevidence retrieval, often from multiple documents. Recen...
Drawing conclusions about real-world relationships of cause and effect from data collected without r...
The scientific claim verification task requires an NLP system to label scientific documents which Su...
While Transformer language models (LMs) are state-of-the-art for information extraction, long text i...
The emergence of Large Language Models (LLMs) has boosted performance and possibilities in various N...
Text-mining algorithms make mistakes in extracting facts from natural-language texts. In biomedical ...
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may con...
Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truth...
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread ...
KGCleaner is a framework to identify and correct errors in data produced and delivered by an informa...
A central question in natural language understanding (NLU) research is whether high performance demo...
While deep neural network models offer unmatched classification performance, they are prone to learn...
Automated fact-checking (AFC) systems exist to combat disinformation, however their complexity usual...
Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-...
Text-mining algorithms make mistakes in extracting facts from natural-language texts. In biomedical ...
A key component of fact verification is thevevidence retrieval, often from multiple documents. Recen...
Drawing conclusions about real-world relationships of cause and effect from data collected without r...
The scientific claim verification task requires an NLP system to label scientific documents which Su...
While Transformer language models (LMs) are state-of-the-art for information extraction, long text i...