PLACES: Prompting language models for social conversation synthesis
Collecting high quality conversational data can be very expensive for most applications and
infeasible for others due to privacy, ethical, or similar concerns. A promising direction to …
infeasible for others due to privacy, ethical, or similar concerns. A promising direction to …
DialFact: A benchmark for fact-checking in dialogue
Fact-checking is an essential tool to mitigate the spread of misinformation and
disinformation. We introduce the task of fact-checking in dialogue, which is a relatively …
disinformation. We introduce the task of fact-checking in dialogue, which is a relatively …
FactKG: Fact verification via reasoning on knowledge graphs
In real world applications, knowledge graphs (KG) are widely used in various domains (eg
medical applications and dialogue agents). However, for fact verification, KGs have not been …
medical applications and dialogue agents). However, for fact verification, KGs have not been …
The choice of textual knowledge base in automated claim checking
Automated claim checking is the task of determining the veracity of a claim given evidence
retrieved from a textual knowledge base of trustworthy facts. While previous work has taken …
retrieved from a textual knowledge base of trustworthy facts. While previous work has taken …
Botstalk: Machine-sourced framework for automatic curation of large-scale multi-skill dialogue datasets
To build open-domain chatbots that are able to use diverse communicative skills, we
propose a novel framework BotsTalk, where multiple agents grounded to the specific target …
propose a novel framework BotsTalk, where multiple agents grounded to the specific target …
Entity-based claim representation improves fact-checking of medical content in tweets
False medical information on social media poses harm to people's health. While the need for
biomedical fact-checking has been recognized in recent years, user-generated medical …
biomedical fact-checking has been recognized in recent years, user-generated medical …
Qadialmoe: Question-answering dialogue based fact verification with mixture of experts
Fact verification is an essential tool to mitigate the spread of false information online, which
has gained a widespread attention recently. However, a fact verification in the question …
has gained a widespread attention recently. However, a fact verification in the question …
Enhancing reliability and user experience in conversational agents
L Aunimo - 2023 World Symposium on Digital Intelligence for …, 2023 - ieeexplore.ieee.org
Conversational agents are in place in a variety of domains and tasks such as sales and
customer support services in business, student counselling in education and medical …
customer support services in business, student counselling in education and medical …
What makes medical claims (un) verifiable? analyzing entity and relation properties for fact verification
A Wührl, YM Resendiz, L Grimminger… - arXiv preprint arXiv …, 2024 - arxiv.org
Biomedical claim verification fails if no evidence can be discovered. In these cases, the fact-
checking verdict remains unknown and the claim is unverifiable. To improve upon this, we …
checking verdict remains unknown and the claim is unverifiable. To improve upon this, we …
An entity-based claim extraction pipeline for real-world biomedical fact-checking
Existing fact-checking models for biomedical claims are typically trained on synthetic or well-
worded data and hardly transfer to social media content. This mismatch can be mitigated by …
worded data and hardly transfer to social media content. This mismatch can be mitigated by …