Large Language Models still struggle in challenging scenarios that leverage structured data, complex reasoning, or tool usage. In this paper, we propose Source2Synth: a new method that can be used for teaching LLMs new skills without relying on costly human annotations. Source2Synth takes as input a custom data source and produces synthetic data points with intermediate reasoning steps grounded in real-world sources. Source2Synth improves the dataset quality by discarding low-quality generations based on their answerability. We demonstrate the generality of this approach by applying it to two challenging domains: we test reasoning abilities in multi-hop question answering (MHQA), and tool usage in tabular question answering (TQA). Our method improves performance by 25.51% for TQA on WikiSQL and 22.57% for MHQA on HotPotQA compared to the fine-tuned baselines.

Multi-agent debate systems are designed to derive accurate and consistent conclusions through adversarial interactions among agents. However, these systems often encounter challenges due to cognitive constraints, manifesting as (1) agents' obstinate adherence to incorrect viewpoints and (2) their propensity to abandon correct viewpoints. These issues are primarily responsible for the ineffectiveness of such debates. Addressing the challenge of cognitive constraints, we introduce a novel framework, the Multi-Agent Debate with Retrieval Augmented (MADRA). MADRA incorporates retrieval of prior knowledge into the debate process, effectively breaking cognitive constraints and enhancing the agents' reasoning capabilities. Furthermore, we have developed a self-selection module within this framework, enabling agents to autonomously select pertinent evidence, thereby minimizing the impact of irrelevant or noisy data. We have comprehensively tested and analyzed MADRA across six diverse datasets. The experimental results demonstrate that our approach significantly enhances performance across various tasks, proving the effectiveness of our proposed method.

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known information. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge. Nonetheless, recent approaches have primarily emphasized retrieval from unstructured text corpora, owing to its seamless integration into prompts. When using structured data such as knowledge graphs, most methods simplify it into natural text, neglecting the underlying structures. Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e.g., knowledge base and text). To fill this gap, we have curated a comprehensive dataset that poses two unique challenges: (1) Two-hop multi-source questions that require retrieving information from both open-domain structured and unstructured knowledge sources; retrieving information from structured knowledge sources is a critical component in correctly answering the questions. (2) The generation of symbolic queries (e.g., SPARQL for Wikidata) is a key requirement, which adds another layer of challenge. Our dataset is created using a combination of automatic generation through predefined reasoning chains and human annotation. We also introduce a novel approach that leverages multiple retrieval tools, including text passage retrieval and symbolic language-assisted retrieval. Our model outperforms previous approaches by a significant margin, demonstrating its effectiveness in addressing the above-mentioned reasoning challenges.

Artificial intelligence has made significant progress in natural language processing, with models like GPT-3 demonstrating impressive capabilities. However, these models still have limitations when it comes to complex tasks that require an understanding of the user, such as mastering human comedy writing strategies. This paper explores humor generation using GPT-3 by modeling human comedy writing theory and leveraging step-by-step thinking instructions. In addition, we explore the role of cognitive distance in creating humor.

Extreme cold is merciless on machinery. Rubber seals stiffen and crack. The problems pile up as the temperature falls. Metal becomes brittle, and wires contract. Batteries stop working, adhesives stop sticking and LCD screens go black as their liquid crystal freezes solid.

They began as tinfoil-like onesies that first took humanity beyond the confines of Earth. But NASA's spacesuits have evolved dramatically through the years to help astronauts survive in the vacuum of space and ultimately allow a man to hop, skip and jump on the moon. Now, the US space agency has revealed its next generation of spacesuit -- expected to be ready for the Artemis III mission that could land the first woman and first person of colour on the lunar surface by 2025. The new suit is said to be a better fit for female space travellers and comes with specialist features to support astronauts as they carry out scientific experiments on the moon. But what were the various spacesuits that came before it?

So the ChatGPT language processing model burst upon an astonished world and the air was rent by squeals of delight and cries of outrage or lamentation. The delighted ones were those transfixed by discovering that a machine could apparently carry out a written commission competently. The outrage was triggered by fears of redundancy on the part of people whose employment requires the ability to write workmanlike prose. And the lamentations came from earnest folks (many of them teachers at various levels) whose day jobs involve grading essays hitherto written by students. If we know anything from history, it is that we generally overestimate the short-term impact of new communication technologies, while grossly underestimating their long-term implications.

On May 25, 1961, President John F. Kennedy delivered a 46-minute speech that included historical context of the Cold War and how the US planned to triumph over the Soviets, but what won the hearts of the American people was his plan to send humans to the moon. 'Space is open to us now; and our eagerness to share its meaning is not governed by the efforts of others. We go into space because whatever mankind must undertake, free men must fully share...,' the late president said while standing behind the lectern during a joint session of Congress. 'First, I believe that this nation should commit itself to achieving the goal, before this decade is out, of landing a man on the moon and returning him safely to the earth.' The US had not even sent a human into orbit at the time of the speech, which placed it far behind the Soviets who had sent an astronaut to space a month before Kennedy addressed the nation.

On July 20, 1969, Neil Armstrong became the first person to walk on the moon. After almost a decade of designing, building, testing, and hypothesizing, we had succeeded -- a man was finally on the moon. Since then we have expanded our sights not only to the moon, but to planets, other moons, and asteroids. Modern space exploration is a vast field of possibilities beyond the limits of Earth's atmosphere where we can increase our knowledge of the cosmos and benefit humanity. As humans, we seek to answer the fundamental questions of our purpose in the universe: Is there life outside of Earth? What are we doing here? Where do we come from? To answer these seemingly endless questions, we look to space, an infinite?

Russia is developing a moon base which will be operated with remote-controlled avatars, according to the country's space boss. Dmitry Rogozin, head of Roscosmos, has laid out plans to put robotic avatars on our natural satellite and have them operated by people on Earth. He claimed this endeavour is more ambitious than the iconic US'Apollo' programme of the '60s and '70s. 'This is about creating a long-term base, naturally, not habitable, but visited. But basically, it is the transition to robotic systems, to avatars that will solve tasks on the Moon surface,' Mr Rogozin said.