Apple could unveil Gemini-powered Siri in Feb. Yahoo Scout will be powered by Claude and is integrated across the company's products. Yahoo has a new AI-powered answer engine, dubbed Yahoo Scout. The new tool is available now in beta and is powered by Anthropic's . The company says Scout synthesizes info from the web, as well as Yahoo's own data and content when constructing responses to user's natural-language search queries. Yahoo says the interface will include interactive digital media, structured lists and tables and visible source links aimed at making answers easier to verify.

No hospital network, government health portal, medical association or academic institution came close to YouTube's number of citations, the researchers said. No hospital network, government health portal, medical association or academic institution came close to YouTube's number of citations, the researchers said. How the'confident authority' of AI Overviews is putting public health at risk Google's search feature AI Overviews cites YouTube more than any medical website when answering queries about health conditions, according to research that raises fresh questions about a tool seen by 2 billion people each month. The company has said its AI summaries, which appear at the top of search results and use generative AI to answer questions from users, are "reliable" and cite reputable medical sources such as the Centers for Disease Control and Prevention and the Mayo Clinic. However, a study that analysed responses to more than 50,000 health queries, captured using Google searches from Berlin, found the top cited source was YouTube .

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information retrieval techniques could be costly and may even introduce noisy and sometimes misleading knowledge. To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose to model whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small amount of seen instances. Extensive experiments demonstrate that Thrust is a good measurement of models' instance-level knowledgeability. Moreover, we can achieve higher cost-efficiency with the Thrust score as the retrieval indicator than the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings shed light on the real-world practice of knowledge-enhanced LMs with a limited budget for knowledge seeking due to computation latency or costs.

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

We consider the query complexity of cake cutting in the standard query model and give lower and upper bounds for computing approximately envy-free, perfect, and equitable allocations with the minimum number of cuts. The lower bounds are tight for computing contiguous envy-free allocations among $n=3$ players and for computing perfect and equitable allocations with minimum number of cuts between $n=2$ players. For $\epsilon$-envy-free allocations with contiguous pieces, we also give an upper bound of $O(n/\epsilon)$ and lower bound of $\Omega(\log(1/\epsilon))$ queries for any number $n \geq 3$ of players.We also formalize moving knife procedures and show that a large subclass of this family, which captures all the known moving knife procedures, can be simulated efficiently with arbitrarily small error in the Robertson-Webb query model.