Text-to-SQL systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (SQL), bridging the gap between non-technical users and complex database management systems. This survey provides a comprehensive overview of the evolution of AI-driven text-to-SQL systems, highlighting their foundational components, advancements in large language model (LLM) architectures, and the critical role of datasets such as Spider, WikiSQL, and CoSQL in driving progress. We examine the applications of text-to-SQL in domains like healthcare, education, and finance, emphasizing their transformative potential for improving data accessibility. Additionally, we analyze persistent challenges, including domain generalization, query optimization, support for multi-turn conversational interactions, and the limited availability of datasets tailored for NoSQL databases and dynamic real-world scenarios. To address these challenges, we outline future research directions, such as extending text-to-SQL capabilities to support NoSQL databases, designing datasets for dynamic multi-turn interactions, and optimizing systems for real-world scalability and robustness. By surveying current advancements and identifying key gaps, this paper aims to guide the next generation of research and applications in LLM-based text-to-SQL systems.

Autoregressive transformer language models (LMs) possess strong syntactic abilities, often successfully handling phenomena from agreement to NPI licensing. However, the features they use to incrementally process language inputs are not well understood. In this paper, we fill this gap by studying the mechanisms underlying garden path sentence processing in LMs. We ask: (1) Do LMs use syntactic features or shallow heuristics to perform incremental sentence processing? (2) Do LMs represent only one potential interpretation, or multiple? and (3) Do LMs reanalyze or repair their initial incorrect representations? To address these questions, we use sparse autoencoders to identify interpretable features that determine which continuation - and thus which reading - of a garden path sentence the LM prefers. We find that while many important features relate to syntactic structure, some reflect syntactically irrelevant heuristics. Moreover, while most active features correspond to one reading of the sentence, some features correspond to the other, suggesting that LMs assign weight to both possibilities simultaneously. Finally, LMs do not re-use features from garden path sentence processing to answer follow-up questions.

A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to high-quality mathematical data. To explore this, we developed an automated method for generating high-quality, supervised mathematical datasets. The method carefully mutates existing math problems, ensuring both diversity and validity of the newly generated problems. This is achieved by a neuro-symbolic data generation framework combining the intuitive informalization strengths of LLMs, and the precise symbolic reasoning of math solvers along with projected Markov chain Monte Carlo sampling in the highly-irregular symbolic space. Empirical experiments demonstrate the high quality of data generated by the proposed method, and that the LLMs, specifically LLaMA-2 and Mistral, when realigned with the generated data, surpass their state-of-the-art counterparts.

Cognitive Diagnosis (CD) aims to evaluate students' cognitive states based on their interaction data, enabling downstream applications such as exercise recommendation and personalized learning guidance. However, existing methods often struggle with accuracy drops in cross-domain cognitive diagnosis (CDCD), a practical yet challenging task. While some efforts have explored exercise-aspect CDCD, such as crosssubject scenarios, they fail to address the broader dual-aspect nature of CDCD, encompassing both student- and exerciseaspect variations. This diversity creates significant challenges in developing a scenario-agnostic framework. To address these gaps, we propose PromptCD, a simple yet effective framework that leverages soft prompt transfer for cognitive diagnosis. PromptCD is designed to adapt seamlessly across diverse CDCD scenarios, introducing PromptCD-S for student-aspect CDCD and PromptCD-E for exercise-aspect CDCD. Extensive experiments on real-world datasets demonstrate the robustness and effectiveness of PromptCD, consistently achieving superior performance across various CDCD scenarios. Our work offers a unified and generalizable approach to CDCD, advancing both theoretical and practical understanding in this critical domain. The implementation of our framework is publicly available at https://github.com/Publisher-PromptCD/PromptCD.

Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize even competition-level math problems. However, we observe a considerable discrepancy between pass@1 and pass@k accuracies in LLM-generated formalizations. To address this gap, we introduce a novel framework that scores and selects the best result from k autoformalization candidates based on two complementary self-consistency methods: symbolic equivalence and semantic consistency. Elaborately, symbolic equivalence identifies the logical homogeneity among autoformalization candidates using automated theorem provers, and semantic consistency evaluates the preservation of the original meaning by informalizing the candidates and computing the similarity between the embeddings of the original and informalized texts. Our extensive experiments on the MATH and miniF2F datasets demonstrate that our approach significantly enhances autoformalization accuracy, achieving up to 0.22-1.35x

The thirty-eighth Conference on Neural Information Processing Systems (NeurIPS 2024) will take place in Vancouver, Canada, from Tuesday 10 December to Sunday 15 December. There is a bumper programme of events, including invited talks, orals, posters, tutorials, workshops, and socials, not to mention AIhub's session on science communication. There are seven invited talks this year: Alison Gopnik – The Golem vs. stone soup: Understanding how children learn can help us understand and improve AI Sepp Hochreiter – Toward industrial artificial intelligence Fei-Fei Li – From seeing to doing: Ascending the ladder of visual intelligence Lidong Zhou – A match made in silicon: The co-evolution of systems and AI Arnaud Doucet – From diffusion models to Schrödinger bridges Danica Kragic – Learning for interaction and interaction for learning Rosalind Picard – How to optimize what matters most? We (AIhub) will be running a short course on science communication on Tuesday 10 December. There will be a total of 14 tutorials this year.

Problems in probability theory prove to be one of the most challenging for students. Here, we formulate and discuss four related problems in probability theory that proved difficult for first to fourth-year undergraduate students whose first language was not English. These examples emphasize how crucial it is to understand the conditions and requirements of the problems precisely before starting to solve them. We discuss the solutions to those problems in detail, complement them with numerical estimations, and link the conditions in the problems to the logical statements in Python programming language. We also tested two widely used chatbots (GPT-4o and Claude 3.5 Sonnet) by checking their responses to these problems.

In the rapidly evolving domain of Artificial Intelligence (AI), the complex interaction between innovation and regulation has become an emerging focus of our society. Despite tremendous advancements in AI's capabilities to excel in specific tasks and contribute to diverse sectors, establishing a high degree of trust in AI-generated outputs and decisions necessitates meticulous caution and continuous oversight. A broad spectrum of stakeholders, including governmental bodies, private sector corporations, academic institutions, and individuals, have launched significant initiatives. These efforts include developing ethical guidelines for AI and engaging in vibrant discussions on AI ethics, both among AI practitioners and within the broader society. This article thoroughly analyzes the ground-breaking AI regulatory framework proposed by the European Union. It delves into the fundamental ethical principles of safety, transparency, non-discrimination, traceability, and environmental sustainability for AI developments and deployments. Considering the technical efforts and strategies undertaken by academics and industry to uphold these principles, we explore the synergies and conflicts among the five ethical principles. Through this lens, work presents a forward-looking perspective on the future of AI regulations, advocating for a harmonized approach that safeguards societal values while encouraging technological advancement.

LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existing benchmarks mostly assess their reasoning abilities in language part, where the chain-of-thought is entirely composed of text.We consider the scenario where visual signals are continuously updated and required along the decision making process. Such vision-in-the-chain reasoning paradigm is more aligned with the needs of multimodal agents, while being rarely evaluated. In this paper, we introduce MageBench, a reasoning capability oriented multimodal agent benchmark that, while having light-weight environments, poses significant reasoning challenges and holds substantial practical value. This benchmark currently includes three types of environments: WebUI, Sokoban, and Football, comprising a total of 483 different scenarios. It thoroughly validates the agent's knowledge and engineering capabilities, visual intelligence, and interaction skills. The results show that only a few product-level models are better than random acting, and all of them are far inferior to human-level. More specifically, we found current models severely lack the ability to modify their planning based on visual feedback, as well as visual imagination, interleaved image-text long context handling, and other abilities. We hope that our work will provide optimization directions for LMM from the perspective of being an agent. We release our code and data at https://github.com/microsoft/MageBench.

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource languages due to limited training data and difficulty in understanding cultural nuances. Research is now focusing on multilingual models to improve LLM performance for these languages. Education in these languages also struggles with a lack of resources and qualified teachers, particularly in underdeveloped regions. Here, LLMs can be transformative, supporting innovative methods like community-driven learning and digital platforms. This paper discusses how LLMs could enhance education for low-resource languages, emphasizing practical applications and benefits.