The tiny shark and a ghost-like crab are two of the latest species uncovered in a yearslong expedition. Breakthroughs, discoveries, and DIY tips sent every weekday. Oceanographers scouring the waters off of Western Australia have discovered two new deep-sea oddities . On October 6, Australia's Commonwealth Scientific and Industrial Research Organization (CSIRO) showcased these new species originally collected in 2022: a bioluminescent lanternshark and a tiny, semi-translucent porcelain crab . The team revealed two of its initial finds--the painted hornshark and the ridged-egg catshark --in 2023.

To achieve equitable performance across languages, multilingual large language models (LLMs) must be able to abstract knowledge beyond the language in which it was acquired. However, the current literature lacks reliable ways to measure LLMs' capability of cross-lingual knowledge transfer. To that end, we present ECLeKTic, a multilingual closed-book QA (CBQA) dataset that Evaluates Cross-Lingual Knowledge Transfer in a simple, black-box manner. We detected information with uneven coverage across languages by controlling for presence and absence of Wikipedia articles in 12 languages. We generated knowledge-seeking questions in a source language, for which the answer appears in a relevant Wikipedia article and translated them to all other 11 languages, for which the respective Wikipedias lack equivalent articles. Assuming that Wikipedia reflects the prominent knowledge in the LLM's training data, to solve ECLeKTic's CBQA task the model is required to transfer knowledge between languages. Experimenting with 8 LLMs, we show that SOTA models struggle to effectively share knowledge across, languages even if they can predict the answer well for queries in the same language the knowledge was acquired in.

Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effectively utilizing the knowledge from retrieved documents, often being misled by irrelevant or noisy information. To address this issue, we introduce RankCoT, a knowledge refinement method that incorporates reranking signals in generating CoT-based summarization for knowledge refinement based on given query and all retrieval documents. During training, RankCoT prompts the LLM to generate Chain-of-Thought (CoT) candidates based on the query and individual documents. It then fine-tunes the LLM to directly reproduce the best CoT from these candidate outputs based on all retrieved documents, which requires LLM to filter out irrelevant documents during generating CoT-style summarization. Additionally, RankCoT incorporates a self-reflection mechanism that further refines the CoT outputs, resulting in higher-quality training data. Our experiments demonstrate the effectiveness of RankCoT, showing its superior performance over other knowledge refinement models. Further analysis reveals that RankCoT can provide shorter but effective refinement results, enabling the generator to produce more accurate answers. All code and data are available at https://github.com/NEUIR/RankCoT.

Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which can be achieved by raising diverse, in-depth, and insightful instructions that deepen interactions. Existing methods target instructions from real instruction dialogues as a learning goal and fine-tune a user simulator for posing instructions. However, the user simulator struggles to implicitly model complex dialogue flows and pose high-quality instructions. In this paper, we take inspiration from the cognitive abilities inherent in human learning and propose the explicit modeling of complex dialogue flows through instructional strategy reuse. Specifically, we first induce high-level strategies from various real instruction dialogues. These strategies are applied to new dialogue scenarios deductively, where the instructional strategies facilitate high-quality instructions. Experimental results show that our method can generate diverse, in-depth, and insightful instructions for a given dialogue history. The constructed multi-turn instructional dialogues can outperform competitive baselines on the downstream chat model.

Kerry Plowright had his feet up and was watching TV one evening late last year when his phone warned of incoming hail. "I was stunned when I walked out the door because there was just this roar," he says, describing the sound of hailstones hitting roofs in the New South Wales town of Kingscliff. He had just enough time to move his cars under canvas sails, sparing them from damage. This season may include a second tropical cyclone to strike Queensland. The Albanese government has launched an inquiry into warnings issued by the Bureau of Meteorology and emergency authorities after complaints by councils and others that some alerts lacked accuracy and timeliness.

We propose a new dataset distillation algorithm using reparameterization and convexification of implicit gradients (RCIG), that substantially improves the state-of-the-art. To this end, we first formulate dataset distillation as a bi-level optimization problem. Then, we show how implicit gradients can be effectively used to compute meta-gradient updates. We further equip the algorithm with a convexified approximation that corresponds to learning on top of a frozen finite-width neural tangent kernel. Finally, we improve bias in implicit gradients by parameterizing the neural network to enable analytical computation of final-layer parameters given the body parameters. RCIG establishes the new state-of-the-art on a diverse series of dataset distillation tasks. Notably, with one image per class, on resized ImageNet, RCIG sees on average a 108\% improvement over the previous state-of-the-art distillation algorithm. Similarly, we observed a 66\% gain over SOTA on Tiny-ImageNet and 37\% on CIFAR-100.

Autonomous Underwater Vehicles (AUVs) conduct regular visual surveys of marine environments to characterise and monitor the composition and diversity of the benthos. The use of machine learning classifiers for this task is limited by the low numbers of annotations available and the many fine-grained classes involved. In addition to these challenges, there are domain shifts between image sets acquired during different AUV surveys due to changes in camera systems, imaging altitude, illumination and water column properties leading to a drop in classification performance for images from a different survey where some or all these elements may have changed. This paper proposes a framework to improve the performance of a benthic morphospecies classifier when used to classify images from a different survey compared to the training data. We adapt the SymmNet state-of-the-art Unsupervised Domain Adaptation method with an efficient bilinear pooling layer and image scaling to normalise spatial resolution, and show improved classification accuracy. We test our approach on two datasets with images from AUV surveys with different imaging payloads and locations. The results show that generic domain adaptation can be enhanced to produce a significant increase in accuracy for images from an AUV survey that differs from the training images.

Summarizing legal decisions requires the expertise of law practitioners, which is both time- and cost-intensive. This paper presents techniques for extractive summarization of legal decisions in a low-resource setting using limited expert annotated data. We test a set of models that locate relevant content using a sequential model and tackle redundancy by leveraging maximal marginal relevance to compose summaries. We also demonstrate an implicit approach to help train our proposed models generate more informative summaries. Our multi-task learning model variant leverages rhetorical role identification as an auxiliary task to further improve the summarizer. We perform extensive experiments on datasets containing legal decisions from the US Board of Veterans' Appeals and conduct quantitative and expert-ranked evaluations of our models. Our results show that the proposed approaches can achieve ROUGE scores vis-\`a-vis expert extracted summaries that match those achieved by inter-annotator comparison.

The ocean is experiencing unprecedented rapid change, and visually monitoring marine biota at the spatiotemporal scales needed for responsible stewardship is a formidable task. As baselines are sought by the research community, the volume and rate of this required data collection rapidly outpaces our abilities to process and analyze them. Recent advances in machine learning enables fast, sophisticated analysis of visual data, but have had limited success in the ocean due to lack of data standardization, insufficient formatting, and demand for large, labeled datasets. To address this need, we built FathomNet, an open-source image database that standardizes and aggregates expertly curated labeled data. FathomNet has been seeded with existing iconic and non-iconic imagery of marine animals, underwater equipment, debris, and other concepts, and allows for future contributions from distributed data sources. We demonstrate how FathomNet data can be used to train and deploy models on other institutional video to reduce annotation effort, and enable automated tracking of underwater concepts when integrated with robotic vehicles. As FathomNet continues to grow and incorporate more labeled data from the community, we can accelerate the processing of visual data to achieve a healthy and sustainable global ocean.

At the outset of World War II, you'd have a better chance of finding a needle in a haystack with a camel stuck in its eye than you did shooting down an enemy aircraft in your first dozen or so shots. This is because anti-aircraft shells at the time used manual fuses that had to be dialed in for specific lengths of time to delay their explosion. The idea was that you'd estimate where the targeted plane would be in, say five seconds, based on its currently flight path, then time the shell for that length, fire the shell at the plane and hope that the timing and location were close enough that shrapnel from the exploding shell hits the plane. If your calculations were off by even a hair, the shell would miss by thousands of feet. And if shooting down piloted aircraft was this hard, intercepting Germany's terrifyingly fast V1 and V2 rockets required far more luck than skill. But that's exactly what the team at Section T set out to do.