Artificial intelligence (AI) has made significant strides in recent years, yet it continues to struggle with a fundamental aspect of cognition present in all animals: common sense. Current AI systems, including those designed for complex tasks like autonomous driving, problem-solving challenges such as the Abstraction and Reasoning Corpus (ARC), and conversational benchmarks like the Turing Test, often lack the ability to adapt to new situations without extensive prior knowledge. This manuscript argues that integrating common sense into AI systems is essential for achieving true autonomy and unlocking the full societal and commercial value of AI. We propose a shift in the order of knowledge acquisition emphasizing the importance of developing AI systems that start from minimal prior knowledge and are capable of contextual learning, adaptive reasoning, and embodiment -- even within abstract domains. Additionally, we highlight the need to rethink the AI software stack to address this foundational challenge. Without common sense, AI systems may never reach true autonomy, instead exhibiting asymptotic performance that approaches theoretical ideals like AIXI but remains unattainable in practice due to infinite resource and computation requirements. While scaling AI models and passing benchmarks like the Turing Test have brought significant advancements in applications that do not require autonomy, these approaches alone are insufficient to achieve autonomous AI with common sense. By redefining existing benchmarks and challenges to enforce constraints that require genuine common sense, and by broadening our understanding of embodiment to include both physical and abstract domains, we can encourage the development of AI systems better equipped to handle the complexities of real-world and abstract environments.

Bridging the significant gap between large language model's English and non-English performance presents a great challenge. While some previous studies attempt to mitigate this gap with translated training data, the recently proposed question alignment approach leverages the model's English expertise to improve multilingual performance with minimum usage of expensive, error-prone translation. In this paper, we explore how broadly this method can be applied by examining its effects in reasoning with executable code and reasoning with common sense. We also explore how to apply this approach efficiently to extremely large language models using proxy-tuning. Experiment results on multilingual reasoning benchmarks mGSM, mSVAMP and xCSQA demonstrate that the question alignment approach can be used to boost multilingual performance across diverse reasoning scenarios, model families, and sizes. For instance, when applied to the LLaMA2 models, our method brings an average accuracy improvements of 12.2% on mGSM even with the 70B model. To understand the mechanism of its success, we analyze representation space, chain-of-thought and translation data scales, which reveals how question translation training strengthens language alignment within LLMs and shapes their working patterns.

We continue the investigation into the power of smaller Transformer-based language models as initiated by \textbf{TinyStories} -- a 10 million parameter model that can produce coherent English -- and the follow-up work on \textbf{phi-1}, a 1.3 billion parameter model with Python coding performance close to the state-of-the-art. The latter work proposed to use existing Large Language Models (LLMs) to generate ``textbook quality" data as a way to enhance the learning process compared to traditional web data. We follow the ``Textbooks Are All You Need" approach, focusing this time on common sense reasoning in natural language, and create a new 1.3 billion parameter model named \textbf{phi-1.5}, with performance on natural language tasks comparable to models 5x larger, and surpassing most non-frontier LLMs on more complex reasoning tasks such as grade-school mathematics and basic coding. More generally, \textbf{phi-1.5} exhibits many of the traits of much larger LLMs, both good -- such as the ability to ``think step by step" or perform some rudimentary in-context learning -- and bad, including hallucinations and the potential for toxic and biased generations -- encouragingly though, we are seeing improvement on that front thanks to the absence of web data. We open-source \textbf{phi-1.5} to promote further research on these urgent topics.

Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, despite their impressive capabilities, diffusion models, such as Stable Diffusion, often struggle to accurately follow the prompts when spatial or common sense reasoning is required. The following figure lists four scenarios in which Stable Diffusion falls short in generating images that accurately correspond to the given prompts, namely negation, numeracy, and attribute assignment, spatial relationships. In contrast, our method, LLM-grounded Diffusion (LMD), delivers much better prompt understanding in text-to-image generation in those scenarios. Figure 1: LLM-grounded Diffusion enhances the prompt understanding ability of text-to-image diffusion models.

Recent advancements in Large Language Models (LLMs) harness linguistic associations in vast natural language data for practical applications. However, their ability to understand the physical world using only language data remains a question. After reviewing existing protocols, we explore this question using a novel and tightly controlled reasoning test (ART) and compare human norms against versions of GPT-3. Our findings highlight the categories of common-sense relations models that could learn directly from data and areas of weakness. GPT-3 offers evidence for verbal reasoning on a par with human subjects for several relations including Synonymy, Antonymy, and Default inheritance, Without reinforcement learning from human judgements, it appears GPT-3 performs at the lower end of the reference interval for Has-part and Contained-in. Weaknesses were observed also in affordance characteristics through Necessary-quality, Order-of-size and Order-of-intensity. Combining LLMs with symbolic world grounding is a promising direction to address associative learning.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. KEAR is a clever architecture to extend transformer models with common sense reasoning.

Successful completion of reasoning task requires the agent to have relevant prior knowledge or some given context of the world dynamics. Usually, the information provided to the system for a reasoning task is just the query or some supporting story, which is often not enough for common reasoning tasks. The goal here is that, if the information provided along the question is not sufficient to correctly answer the question, the model should choose k most relevant documents that can aid its inference process. In this work, the model dynamically selects top k most relevant memory candidates that can be used to successfully solve reasoning tasks. Experiments were conducted on a subset of Winograd Schema Challenge (WSC) problems to show that the proposed model has the potential for commonsense reasoning. The WSC is a test of machine intelligence, designed to be an improvement on the Turing test.

What do the games of chess, Jeopardy!, Go, Texas Hold'em, and StarCraft have in common? In each of these competitive arenas, an AI has resoundingly beat the best human players in the world. These victories are astounding feats of artificial intelligence--yet they've become almost humdrum. At the Allen Institute for Artificial Intelligence (AI2), in Seattle, researchers set out to do something different. Their AllenAI collaborates with a human player in a Pictionary-style drawing and guessing game, which is won through human-AI cooperation.

Nearly half a century has passed between the release of the films 2001: A Space Odyssey (1968) and Transcendence (2014), in which a quirky scientist's consciousness is uploaded into a computer. Despite being 50 years apart, their plots, however, are broadly similar. Science fiction stories continue to imagine the arrival of human-like machines that rebel against their creators and gain the upper hand in battle. In the field of artificial intelligence (AI) research, over the last 30 years, progress has been similarly slower than expected. While AI is increasingly part of our everyday lives - in our phones or cars - and computers process large amounts of data, they still lack human-level capacity to make deductions from the information they're given.

We present an approach for cyberbullying detection based on state-of-the-art text classification and a common sense knowledge base, which permits recognition over a broad spectrum of topics in everyday life. We analyze a more narrow range of particular subject matter associated with bullying and construct BullySpace, a common sense knowledge base that encodes particular knowledge about bullying situations. We then perform joint reasoning with common sense knowledge about a wide range of everyday life topics. We analyze messages using our novel AnalogySpace common sense reasoning technique. We also take into account social network analysis and other factors. We evaluate the model on real-world instances that have been reported by users on Form spring, a social networking website that is popular with teenagers. On the intervention side, we explore a set of reflective user interaction paradigms with the goal of promoting empathy among social network participants. We propose an air traffic control-like dashboard, which alerts moderators to large-scale outbreaks that appear to be escalating or spreading and helps them prioritize the current deluge of user complaints. For potential victims, we provide educational material that informs them about how to cope with the situation, and connects them with emotional support from others. A user evaluation shows that in context, targeted, and dynamic help during cyberbullying situations fosters end-user reflection that promotes better coping strategies.