With the proliferation of social media, accurate detection of hate speech has become critical to ensure safety online. To combat nuanced forms of hate speech, it is important to identify and thoroughly explain hate speech to help users understand its harmful effects. Recent benchmarks have attempted to tackle this issue by training generative models on free-text annotations of implications in hateful text. However, we find significant reasoning gaps in the existing annotations schemes, which may hinder the supervision of detection models. In this paper, we introduce a hate speech detection framework, HARE, which harnesses the reasoning capabilities of large language models (LLMs) to fill these gaps in explanations of hate speech, thus enabling effective supervision of detection models. Experiments on SBIC and Implicit Hate benchmarks show that our method, using model-generated data, consistently outperforms baselines, using existing free-text human annotations. Analysis demonstrates that our method enhances the explanation quality of trained models and improves generalization to unseen datasets. Our code is available at https://github.com/joonkeekim/hare-hate-speech.git.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. A cold case team that combed through evidence for five years in a bid to unravel one of World War II's enduring mysteries has reached what it calls the "most likely scenario" of who betrayed Jewish teenage diarist Anne Frank and her family. Their answer, outlined in a new book called "The Betrayal of Anne Frank A Cold Case Investigation," by Canadian academic and author Rosemary Sullivan, is that it could have been prominent Jewish notary Arnold van den Bergh who disclosed the secret annex hiding place of the Frank family to German occupiers to save his own family from deportation and murder in Nazi concentration camps. "We have investigated over 30 suspects in 20 different scenarios, leaving one scenario we like to refer to as the most likely scenario," said filmmaker Thijs Bayens, who had the idea to put together the cold case team, which was led by retired FBI agent Vincent Pankoke, to forensically examine the evidence.

For nearly 75 years, some of the greatest investigative minds have tried to figure out who tipped off the Nazis about Anne Frank and the seven other Jews who were hiding behind a movable bookcase in Amsterdam. Now, a former FBI investigator working with a production company hopes the decades-old mystery can be solved with the help of a new mind -- an artificial one. Vince Pankoke, who spent a chunk of his FBI career investigating Colombian drug cartels, has assembled a team of 20 researchers, data analysts and historians to look into what he calls "one of the biggest cold cases" of the 20th century. The most unconventional member of his team is a piece of specialized software that can cross-reference millions of documents -- police reports, lists of Nazi spies, investigative files for Frank family sympathizers -- to find connections and new leads.

In August of 1944, Anne Frank and her family were captured by the Gestapo after spending a gruelling two years hidden in a secret annex within their apartment. The prolific diarist's work would posthumously bring her fame and recognition the world over. But, to this day, no one has been able to identify who was behind the betrayal that led to her death in a concentration camp. Fast forward 73 years, and a former FBI agent is betting artificial intelligence can help crack the mystery. Retired sleuth Vincent Pankoke, and his team of investigators (comprised of forensic scientists and members of the Dutch police force), are partnering with Amsterdam-based data company Xomnia on the ultimate cold case. As part of the newly-opened enquiry, a specially developed algorithm will scour reams of documents from the period.

In August of 1944, Anne Frank and her family were captured by the Gestapo after spending a gruelling two years hidden in a secret annex within their apartment. The prolific diarist's work would posthumously bring her fame and recognition the world over. But, to this day, no one has been able to identify who was behind the betrayal that led to her death in a concentration camp. Fast forward 73 years, and a former FBI agent is betting artificial intelligence can help crack the mystery. Retired sleuth Vincent Pankoke, and his team of investigators (comprised of forensic scientists and members of the Dutch police force), are partnering with Amsterdam-based data company Xomnia on the ultimate cold case. As part of the newly-opened enquiry, a specially developed algorithm will scour reams of documents from the period.