Large language models excel at many tasks but often incur high inference costs during deployment. To mitigate hallucination, many systems use a knowledge graph to enhance retrieval-augmented generation (KG-RAG). However, the large amount of retrieved knowledge contexts increase these inference costs further. A promising solution to balance performance and cost is LLM routing, which directs simple queries to smaller LLMs and complex ones to larger LLMs. However, no dedicated routing methods currently exist for RAG, and existing training-based routers face challenges scaling to this domain due to the need for extensive training data. We observe that the score distributions produced by the retrieval scorer strongly correlate with query difficulty. Based on this, we propose an extremely simple yet effective routing framework, the first specifically designed for KG-RAG that efficiently balances performance and cost in a plug-and-play manner. It delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods. Our code is available at https://github.com/hrwang00/SkewRoute.

Fox News Flash top sports headlines are here. Check out what's clicking on Foxnews.com. Pitcher Justin Garza was thinking about quitting the game he loved during the COVID-19 pandemic in 2020 as he struggled in the minor leagues. However, as Garza is joining the New York Mets now after a deal with the San Francisco Giants, he credits one thing to saving his career. Boston Red Sox starting pitcher Justin Garza, #63, reacts after giving up a home run to Minnesota Twins designated hitter Byron Buxton during the first inning at Target Field.

Although Large Language Models achieve strong success in many tasks, they still suffer from hallucinations and knowledge deficiencies in real-world applications. Many knowledge graph-based retrieval-augmented generation (KG-RAG) methods enhance the quality and credibility of LLMs by leveraging structure and semantic information in KGs as external knowledge bases. However, these methods struggle to effectively incorporate structure information, either incurring high computational costs or underutilizing available knowledge. Inspired by smoothing operations in graph representation learning, we propose path pooling, a simple, train-free strategy that introduces structure information through a novel path-centric pooling operation. It seamlessly integrates into existing KG-RAG methods in a plug-and-play manner, enabling richer structure information utilization. Extensive experiments demonstrate that incorporating the path pooling into the state-of-the-art KG-RAG method consistently improves performance across various settings while introducing negligible additional cost. Code is coming soon at https://github.com/hrwang00/path-pooling.

Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM outputs in structured external knowledge from KGs. However, current KG-based RAG frameworks still struggle to optimize the trade-off between retrieval effectiveness and efficiency in identifying a suitable amount of relevant graph information for the LLM to digest. We introduce SubgraphRAG, extending the KG-based RAG framework that retrieves subgraphs and leverages LLMs for reasoning and answer prediction. Our approach innovatively integrates a lightweight multilayer perceptron with a parallel triple-scoring mechanism for efficient and flexible subgraph retrieval while encoding directional structural distances to enhance retrieval effectiveness. The size of retrieved subgraphs can be flexibly adjusted to match the query's need and the downstream LLM's capabilities. This design strikes a balance between model complexity and reasoning power, enabling scalable and generalizable retrieval processes. Notably, based on our retrieved subgraphs, smaller LLMs like Llama3.1-8B-Instruct deliver competitive results with explainable reasoning, while larger models like GPT-4o achieve state-of-the-art accuracy compared with previous baselines -- all without fine-tuning. Extensive evaluations on the WebQSP and CWQ benchmarks highlight SubgraphRAG's strengths in efficiency, accuracy, and reliability by reducing hallucinations and improving response grounding.

Digital assistants like Amazon's Echo can listen to you. And they can talk back. But that doesn't mean they can carry on a good conversation. As the devices that run these assistants become more commonplace -- 39 million Americans now own one, according to a recent study -- Amazon and competitors like Apple and Google foresee a day when you can chat with their assistants as you would with a friend. After consulting with the companies involved and a few artificial intelligence experts we created tests that show what they can and can't handle.

It's no secret that when it comes to voice assistants, Siri is often cited as one of the worst. Even though Apple introduced it years before Amazon and Google, their digital rivals -- Alexa and Google Assistant -- have since bested Siri in both features and performance. That's mostly because Amazon and Google have spent years pouring millions of dollars worth of research into artificial intelligence, making their assistants smarter and more capable over time. Apple is trying to catch up. Not only is it beefing up its phones with "neural engine" chips to power AI efforts like augmented reality and machine learning, it's also building out its Siri team.

The iPhone has been my primary smartphone for well over a decade, and therefore I've had Siri on my phone ever since its introduction in 2011. But I never really found a reason to use it. I've always felt self-conscious when talking to my phone -- I find people who use voice commands in public really annoying -- so I wanted to avoid doing it myself. I have Bluetooth in my car so I don't have to use my phone while driving, and when I'm at home, I have my trusty fingers instead. So I imagined that being forced to use Siri for a whole week was going to be a nightmare.