Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose MR.COD (Multi-hop evidence retrieval for Cross-document relation extraction), which is a multi-hop evidence retrieval method based on evidence path mining and ranking. We explore multiple variants of retrievers to show evidence retrieval is essential in cross-document RE. We also propose a contextual dense retriever for this setting. Experiments on CodRED show that evidence retrieval with MR.COD effectively acquires crossdocument evidence and boosts end-to-end RE performance in both closed and open settings.

Conversational search allows a user to interact with a search system in multiple turns. A query is strongly dependent on the conversation context. An effective way to improve retrieval effectiveness is to expand the current query with historical queries. However, not all the previous queries are related to, and useful for expanding the current query. In this paper, we propose a new method to select relevant historical queries that are useful for the current query. To cope with the lack of labeled training data, we use a pseudo-labeling approach to annotate useful historical queries based on their impact on the retrieval results. The pseudo-labeled data are used to train a selection model. We further propose a multi-task learning framework to jointly train the selector and the retriever during fine-tuning, allowing us to mitigate the possible inconsistency between the pseudo labels and the changed retriever. Extensive experiments on four conversational search datasets demonstrate the effectiveness and broad applicability of our method compared with several strong baselines.

Generative deep learning models are able to create realistic audio and video. This technology has been used to impersonate the faces and voices of individuals. These ``deepfakes'' are being used to spread misinformation, enable scams, perform fraud, and blackmail the innocent. The technology continues to advance and today attackers have the ability to generate deepfakes in real-time. This new capability poses a significant threat to society as attackers begin to exploit the technology in advances social engineering attacks. In this paper, we discuss the implications of this emerging threat, identify the challenges with preventing these attacks and suggest a better direction for researching stronger defences.

We propose a shared task of human-like long text generation, LTG Challenge, that asks models to output a consistent human-like long text (a Harry Potter generic audience fanfic in English), given a prompt of about 1000 tokens. We suggest a novel statistical metric of the text structuredness, GloVe Autocorrelations Power/ Exponential Law Mean Absolute Percentage Error Ratio (GAPELMAPER) and a human evaluation protocol. We hope that LTG can open new avenues for researchers to investigate sampling approaches, prompting strategies, autoregressive and non-autoregressive text generation architectures and break the barrier to generate consistent long (40K+ token) texts.

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and contribute to the propagation of harmful stereotypes. This work utilises the flaw of bias in language models to explore the biases of six different online communities. In order to get an insight into the communities' viewpoints, we fine-tune GPT-Neo 1.3B with six social media datasets. The bias of the resulting models is evaluated by prompting the models with different demographics and comparing the sentiment and toxicity values of these generations. Together, these methods reveal that bias differs in type and intensity for the various models. This work not only affirms how easily bias is absorbed from training data but also presents a scalable method to identify and compare the bias of different datasets or communities. Additionally, the examples generated for this work demonstrate the limitations of using automated sentiment and toxicity classifiers in bias research.

Alarm over artificial intelligence has reached a fever pitch in recent months. Just this week, more than 300 industry leaders published a letter warning AI could lead to human extinction and should be considered with the seriousness of "pandemics and nuclear war". Terms like "AI doomsday" conjure up sci-fi imagery of a robot takeover, but what does such a scenario actually look like? The reality, experts say, could be more drawn out and less cinematic – not a nuclear bomb but a creeping deterioration of the foundational areas of society. "I don't think the worry is of AI turning evil or AI having some kind of malevolent desire," said Jessica Newman, director of University of California Berkeley's Artificial Intelligence Security Initiative.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Extremist rebels in eastern Congo killed at least nine people with knives and guns, a civil society organization said Friday. The attack happened Thursday evening on the Kyondo-Kyavinyonge road in North Kivu province, said Meleki Mulala the coordinator for the Congolese civil society group for the Ruwenzori sector. Civilians were taken from their homes before they were killed, and many homes were looted, he said.

Today, Artifact is taking another jump on the generative-AI rocket ship in an attempt to address an annoying problem--clickbaity headlines. The app already offers a way for users to flag clickbait stories, and if multiple people tag an article, Artifact won't spread it. But, Systrom explains, sometimes the problem isn't with the story but the headline. It might promise too much, or mislead, or lure the reader into clicking just to find some information that's held back from the headline. From the publisher's viewpoint, winning more clicks is a big plus--but it's frustrating to users, who might feel they have been manipulated.

The future of Hollywood looks a lot like Deepfake Ryan Reynolds selling you a Tesla. In a video, since removed but widely shared on Twitter, the actor is bespectacled in thick black frames, his mouth mouthing independently from his face, hawking electric vehicles: "How much do you think it would cost to own a car that's this fucking awesome?" On the verisimilitude scale, the video, which originally circulated last month, registered as blatantly unreal. Then its creator, financial advice YouTuber Kevin Paffrath, revealed he had made it as a ploy to attract the gaze of Elon Musk. Elsewhere on Twitter, people beseeched Reynolds to sue.

Congress knows artificial Intelligence will impact American jobs, but what should lawmakers do about it? They're not entirely sure, but they are concerned. WASHINGTON, D.C. – Congressional lawmakers told Fox News they're concerned about how artificial Intelligence will impact the job market, but were unsure how to approach the issue. "I don't have answers," Rep. Adam Smith, a Democrat, said. "There's no question AI is an incredibly disruptive technology, and we should be closely looking at the implications of it and how best to handle those implications."