Improving factual consistency of abstractive summarization has been a widely studied topic. However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality. We propose EFACTSUM (i.e., Effective Factual Summarization), a candidate summary generation and ranking technique to improve summary factuality without sacrificing summary quality. We show that using a contrastive learning framework with our refined candidate summaries leads to significant gains on both factuality and similarity-based metrics. Specifically, we propose a ranking strategy in which we effectively combine two metrics, thereby preventing any conflict during training. Models trained using our approach show up to 6 points of absolute improvement over the base model with respect to FactCC on XSUM and 11 points on CNN/DM, without negatively affecting either similarity-based metrics or absractiveness.

The White House has made responsible AI development a focus of this administration in recent months, releasing a Blueprint AI Bill of Rights, developing a risk management framework, committing $140 million to found seven new National Academies dedicated to AI research and weighing in on how private enterprises are leveraging the technology. On Tuesday, the executive branch announced its next steps towards that goal including releasing an update to the National AI R&D Strategic Plan for the first time since 2019 as well as issuing a request for public input on critical AI issues. The Department of Education also dropped its hotly-anticipated report on the effects and risks of AI for students. The OSTP's National AI R&D Strategic Plan, which guides the federal government's investments in AI research, hadn't been updated since the Trump Administration (when he gutted the OSTP staffing levels). The plan seeks to promote responsible innovation in the field that serves the public good without infringing on the public's rights, safety and democratic values, having done so until this point through eight core strategies.

The Biden administration on Tuesday sought input from the public on how to ensure artificial intelligence develops in a way that supports "equity" and civil rights and helps "underserved communities," as part of a broader plan to promote "responsible" AI. The White House Office of Science and Technology Policy (OSTP) announced it is seeking input from any interested party on how to reach these and other goals as AI systems are developed. Policymakers and AI developers are increasingly in agreement on the need for federal rules, and possibly even a new federal agency, to ensure the risks of AI are managed. To inform this work, OSTP asked a series of questions on how to protect people's rights and safety as AI systems become more widely used, as well as questions related to "advancing equity and strengthening civil rights. HERE'S HOW AI IS BEING USED TO UNLOCK SECRETS STILL HIDDEN IN THE HUMAN BRAIN President Biden on Tuesday released a new plan for government research into AI, and the White House Office of Science and Technology Policy is asking how to make sure AI boosts'equity.' (Photo by Drew Angerer/Getty Images) "What are the opportunities for AI to enhance equity and how can these be fostered?" "For example, what are the potential benefits for AI in enabling broadened prosperity, expanding economic and educational opportunity, increasing access to services, and advancing civil rights?

WASHINGTON--The Biden administration took another step Tuesday toward regulating new artificial intelligence tools such as ChatGPT, asking for public input as it seeks to develop a national AI strategy to guard against misinformation and other potential downsides of the technology.

OpenAI Chief Executive Officer Sam Altman said part of the reason for his current tour of European cities is to discover a suitable location for a new office. "Poland would be an interesting place," Altman said in an interview Tuesday when asked about European offices. "We want to do a research and engineering office in Europe, not a regulatory one. We are trying to figure it out. This is part of the goal of this trip."

FALLING FLAT - Bud Light reportedly forced to take action after beer remains unsold, expires on shelves. CUTTING EDGE - Here's how AI is being used to unlock secrets in the human brain. NO BEANS - Durham report guts left's narrative but one group still disbelieves, writes Mark Penn. SUSTAINED DROUGHT - Biden admin announces'historic' plan to reduce western states' water supply. HEIR APPARENT - Senator won't seek another term, paving way for Democrat rising star.

Rapid advances in artificial intelligence (AI) such as Microsoft-backed OpenAI's ChatGPT are complicating governments' efforts to agree to laws governing the use of the technology. The government is consulting Australia's main science advisory body and is considering the next steps, a spokesperson for the industry and science minister said in April. The Financial Conduct Authority, one of several state regulators tasked with drawing up new guidelines covering AI, is consulting with the Alan Turing Institute and other legal and academic institutions to improve its understanding of the technology, a spokesperson said. Britain's competition regulator said on May 4 it would start examining the effect of AI on consumers, businesses and the economy, and whether new controls were needed. Britain said in March it planned to split responsibility for governing AI between its regulators for human rights, health and safety, and competition, rather than creating a new body. China's cyberspace regulator in April unveiled draft measures to manage generative AI services, saying it wanted firms to submit security assessments to authorities before they launch offerings to the public.

Last week, OpenAI CEO Sam Altman appeared before a US Senate committee to talk about the risks and potential of AI language models. Altman, along with many senators, called for international standards for artificial intelligence. He also urged the US to regulate the technology and set up a new agency, much like the Food and Drug Administration, to regulate AI. For an AI policy nerd like myself, the Senate hearing was both encouraging and frustrating. Encouraging because the conversation seems to have moved past promoting wishy-washy self-regulation and on to rules that could actually hold companies accountable.

Capps warned against high-stakes use of black box AI due to the lack of transparency behind the technology's decision-making process. New developments in artificial intelligence have thrust the technology to the forefront of public discord, but also raised concerns about the opaque decision-making process of some systems – often referred to as "black box AI." The term "black box" came from Great Britain's Royal Air Force during WWII, Dr. Michael Capps told Fox News Digital. But when it relates to AI, the term is used to describe a decision-making process that cannot be explained. "The whole idea of a black box is you're not allowed to look inside and see, and that's what we have with these artificial neural networks, with hundreds of billions of nodes inside of a box, that nobody can look into," Capps said.

Existing factual consistency evaluation approaches for text summarization provide binary predictions and limited insights into the weakness of summarization systems. Therefore, we propose the task of fine-grained inconsistency detection, the goal of which is to predict the fine-grained types of factual errors in a summary. Motivated by how humans inspect factual inconsistency in summaries, we propose an interpretable fine-grained inconsistency detection model, FineGrainFact, which explicitly represents the facts in the documents and summaries with semantic frames extracted by semantic role labeling, and highlights the related semantic frames to predict inconsistency. The highlighted semantic frames help verify predicted error types and correct inconsistent summaries. Experiment results demonstrate that our model outperforms strong baselines and provides evidence to support or refute the summary.