Providing Language Models (LMs) with relevant evidence in the context (either via retrieval or user-provided) can significantly improve their ability to provide factually correct grounded responses. However, recent studies have found that LMs often struggle to fully comprehend and utilize key evidence from the context, especially when it contains noise and irrelevant information - an issue common in real-world scenarios. To address this, we propose SelfElicit, an inference-time approach that helps LMs focus on key contextual evidence through self-guided explicit highlighting. By leveraging the inherent evidence-finding capabilities of LMs using the attention scores of deeper layers, our method automatically identifies and emphasizes key evidence within the input context, facilitating more accurate and factually grounded responses without additional training or iterative prompting. We demonstrate that SelfElicit brings consistent and significant improvement on multiple evidence-based QA tasks for various LM families while maintaining computational efficiency. Our code and documentation are available at https://github.com/ZhiningLiu1998/SelfElicit.

In medieval Europe, barber-surgeons might cut your hair, shave your face, do a bit of blood-letting and tend to a broken limb. They might also pull a tooth out with a "pelican" – a crude beak-like shank – or lever it out with an iron "tooth key". By the 17th century they might just knock it out with a steel punch elevator. It's a winding, gruesome road from these early practitioners of dentistry to today's world of 3D printing, artificial intelligence and robots that can create dental implants. Wayne Sampson, a dental historian and emeritus professor at the University of Adelaide, says the history of dental work goes back much further than the barber-surgeons.

With El Niño slated to drop a warm, wet winter on most of the US in the coming months, everybody's going to need something good to read while the weather outside is frightful. Engadget's well-read staff have some suggestions: our favorite books of 2023! We've got a phenomenal assortment of genres and titles for you this year, from horror and true crime to rom-coms and fantasy adventures, here to provide months of entertainment for even the most voracious reader. I love horror movies but horror novels are kind of hit and miss for me. I was immediately pulled into Final Girl Support Group, though, which does a lot of winking and nodding at classic slasher flicks while creating a completely unique story. Grady Hendrix's novel doesn't satirize the final girl, but imagines what life might be like for them after the end of their movie. Each of the main characters is (loosely) based on the final girl of a classic slasher, though their storylines don't feel contrived or predictable. It reads like a fast-paced thriller but, like so many of the best horror movies, it's also a poignant reflection on trauma.

Research led by Monash University, RMIT and the University of Adelaide has developed an accurate method of controlling optical circuits on fingernail-sized photonic integrated circuits. The development, published in the prestigious international journal Optica builds on the work by the same team who recently created the world's first self-calibrated photonic chip. Photonics, or the use of light particles to store and transmit information, is a burgeoning field, supporting our need to create faster, better, more efficient and more sustainable technology. Programmable photonic integrated circuits (PICs), offer diverse signal processing functions within a single chip, and present promising solutions for applications ranging from optical communications to artificial intelligence. Whether it's downloading movies or keeping a satellite on course, photonics is radically changing the way we live, revolutionising the processing capability of large scale equipment onto a chip the size of a human fingernail.

The University of Adelaide and MTX Group have entered into a research collaboration to develop new insights in machine learning (ML) and artificial intelligence (AI). Bringing together their academic research and commercial expertise and experience, the two organisations will undertake specific, outcomes-focussed research. They will use AI to model uncertainty with a view to avoiding failure within systems that may be used in defence and business environments. The University and MTX Group have jointly been awarded $100,000 under the Artificial Intelligence for Decision Making Initiative which is a collaborative project between the Australian Government's Office of National Intelligence (ONI) and the Defence Science and Technology Group (DST). Dr Duong Nguyen and Dr George Stamatescu from the University's School of Computer Science will work alongside Dr Ammar Mohemmed from MTX Group.

From The Jetsons to Harry Potter, flying cars have been staple features of science fiction blockbusters for years. But the futuristic vehicles are now very much a reality, with some even competing in races in the skies. This week, two remote-controlled flying race cars competed in a track race in the skies over Adelaide for the first time, as part of the Airspeeder series. The race saw pilots Zephatiali Walsh and Fabio Tischler go head-to-head, piloting two 13.5ft-long flying race cars remotely from the ground. Walsh took home the gold in the inaugural 0.6-mile race, and said he'couldn't be prouder'.

One key challenge in multi-document summarization is to capture the relations among input documents that distinguish between single document summarization (SDS) and multi-document summarization (MDS). Few existing MDS works address this issue. One effective way is to encode document positional information to assist models in capturing cross-document relations. However, existing MDS models, such as Transformer-based models, only consider token-level positional information. Moreover, these models fail to capture sentences' linguistic structure, which inevitably causes confusions in the generated summaries. Therefore, in this paper, we propose document-aware positional encoding and linguistic-guided encoding that can be fused with Transformer architecture for MDS. For document-aware positional encoding, we introduce a general protocol to guide the selection of document encoding functions. For linguistic-guided encoding, we propose to embed syntactic dependency relations into the dependency relation mask with a simple but effective non-linear encoding learner for feature learning. Extensive experiments show the proposed model can generate summaries with high quality.

Zbigniew Michalewicz is Emeritus Professor of Computer Science at the University of Adelaide in Australia. He completed his Masters degree at Technical University of Warsaw in 1974 and he received Ph.D. degree from the Institute of Computer Science, Polish Academy of Sciences, in 1981. He also holds a Doctor of Science degree in Computer Science from the Polish Academy of Science. Zbigniew Michalewicz also holds Professor positions at the Institute of Computer Science, Polish Academy of Sciences, the Polish-Japanese Institute of Information Technology, and the State Key Laboratory of Software Engineering of Wuhan University, China. He is also associated with the Structural Complexity Laboratory at Seoul National University, South Korea.

In the southeast of South Australia lie the Naracoorte Caves. The national park is an UNESCO World Heritage Site known for its stalactites, stalagmites and prehistoric fossils. Recently, a group of students from the University of Adelaide built a robot to complete a 3D scan of the site. The project, called CaveX, saw the group create 15 iterations of the model you see above before they settled on a final design. They went with a robot that walks on a set of six legs out of a fear that one with treads or wheels would damage the surface of the caves.

Avatars: In this year's inaugural Grands Prix, the locations for which are yet to be revealed, 'telerobotic avatars' named'The Aviators' will sit in the'octocopter' race car The craft sports eight rotor blades surrounding a central carbon-fibre cockpit and is capable of going from 0-62 miles per hour in 2.8 seconds. Lewis Hamilton in a Mercedes F1 car would be able to do the same in around 2.6 seconds