In-context learning (ICL) allows a language model to improve its problem-solving capability when provided with suitable information in context. Since the choice of in-context information can be determined based on the problem itself, in-context learning is analogous to human learning from teachers in a classroom. Recent works (Didolkar et al., 2024a; 2024b) show that ICL performance can be improved by leveraging a frontier large language model's (LLM) ability to predict required skills to solve a problem, popularly referred to as an LLM's metacognition, and using the recommended skills to construct necessary in-context examples. While this skill-based strategy boosts ICL performance in larger models, its gains on small language models (SLMs) have been minimal, highlighting a performance gap in ICL capabilities. We investigate this gap and show that skill-based prompting can hurt SLM performance on easy questions by introducing unnecessary information, akin to cognitive overload. To address this, we introduce AdaptMI, an adaptive approach to selecting skill-based in-context Math Instructions for SLMs. Inspired by cognitive load theory from human pedagogy, our method only introduces skill-based examples when the model performs poorly. We further propose AdaptMI+, which adds examples targeted to the specific skills missing from the model's responses. On 5-shot evaluations across popular math benchmarks and five SLMs (1B--7B; Qwen, Llama), AdaptMI+ improves accuracy by up to 6% over naive skill-based strategies.

Many real world tasks where Large Language Models (LLMs) can be used require spatial reasoning, like Point of Interest (POI) recommendation and itinerary planning. However, on their own LLMs lack reliable spatial reasoning capabilities, especially about distances. To address this problem, we develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training. Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question. Using this technique, our method enables an LLM to answer distance-based reasoning questions that it otherwise cannot answer. Given the vast array of possible places an LLM could be asked about, DistRAG offers a flexible first step towards providing a rudimentary `world model' to complement the linguistic knowledge held in LLMs.

This study introduces a novel method that employs tag annotation coupled with the ChatGPT language model to analyze student learning behaviors and generate personalized feedback. Central to this approach is the conversion of complex student data into an extensive set of tags, which are then decoded through tailored prompts to deliver constructive feedback that encourages rather than discourages students. This methodology focuses on accurately feeding student data into large language models and crafting prompts that enhance the constructive nature of feedback. The effectiveness of this approach was validated through surveys conducted with over 20 mathematics teachers, who confirmed the reliability of the generated reports. This method can be seamlessly integrated into intelligent adaptive learning systems or provided as a tool to significantly reduce the workload of teachers, providing accurate and timely feedback to students. By transforming raw educational data into interpretable tags, this method supports the provision of efficient and timely personalized learning feedback that offers constructive suggestions tailored to individual learner needs.

Earlier this year, Bad Bunny emphatically rejected rumors that he was about to release a new song with Justin Bieber. "That's fake," he told TIME in an interview for a cover story on his meteoric rise. "You never know what I'm going to do." But last month, a song featuring what sounded like his and Bieber's voices started circulating on TikTok, garnering millions of likes. Bad Bunny hadn't lied in the interview, though: the song was created with AI.

Now we are getting to the biggest and weirdest risk of AI: a super intelligence emerging and wiping out humanity in pursuit of its own goals. To a lot of people this seems like a totally absurd idea, held only by a tiny fringe of people who appear weird and borderline culty. It seems so far out there and also so huge that most people wind up dismissing it and/or forgetting about shortly after hearing it. There is a big similarity here to the climate crisis, where the more extreme views are widely dismissed. In case you have not encountered the argument yet, let me give a very brief summary (Nick Bostrom has an entire book on the topic and Eliezer Yudkowsky has been blogging about it for two decades, so this will be super compressed by comparison): A superintelligence when it emerges will be pursuing its own set of goals.

AI language models trained on Web data generate prose that reflects human knowledge and public sentiments, but can also contain novel insights and predictions. We asked the world's best language model, GPT-3, fifteen difficult questions about the nature, value, and future of library and information science (LIS), topics that receive perennial attention from LIS scholars. We present highlights from its 45 different responses, which range from platitudes and caricatures to interesting perspectives and worrisome visions of the future, thus providing an LIS-tailored demonstration of the current performance of AI language models. We also reflect on the viability of using AI to forecast or generate research ideas in this way today. Finally, we have shared the full response log online for readers to consider and evaluate for themselves.

Research has shown that trust is an essential aspect of human-computer interaction directly determining the degree to which the person is willing to use a system. An automatic prediction of the level of trust that a user has on a certain system could be used to attempt to correct potential distrust by having the system take relevant actions like, for example, apologizing or explaining its decisions. In this work, we explore the feasibility of automatically detecting the level of trust that a user has on a virtual assistant (VA) based on their speech. We developed a novel protocol for collecting speech data from subjects induced to have different degrees of trust in the skills of a VA. The protocol consists of an interactive session where the subject is asked to respond to a series of factual questions with the help of a virtual assistant. In order to induce subjects to either trust or distrust the VA's skills, they are first informed that the VA was previously rated by other users as being either good or bad; subsequently, the VA answers the subjects' questions consistently to its alleged abilities. All interactions are speech-based, with subjects and VAs communicating verbally, which allows the recording of speech produced under different trust conditions. Using this protocol, we collected a speech corpus in Argentine Spanish. We show clear evidence that the protocol effectively succeeded in influencing subjects into the desired mental state of either trusting or distrusting the agent's skills, and present results of a perceptual study of the degree of trust performed by expert listeners. Finally, we found that the subject's speech can be used to detect which type of VA they were using, which could be considered a proxy for the user's trust toward the VA's abilities, with an accuracy up to 76%, compared to a random baseline of 50%.

Christoph Lutge, director of the Institute for Ethics in Artificial Intelligence at Germany's Technical University of Munich, said there is "a chance that these AI systems might be fairer eventually, but they will need guidelines." In January, the Institute for Ethics in Artificial Intelligence was established at Germany's Technical University of Munich (TUM), with initial funding from a five-year, $7.5-million grant from Facebook. The Institute has issued its first call for proposals, and an advisory board was recently appointed. The Institute's director, Christoph Lütge, holds the Peter Löscher Chair in Business Ethics at TUM. Lütge recently spoke about ethics in artificial intelligence (AI) generally, and the new Institute specifically. Can you give an example of the type of ethical question in AI that the Center might be dealing with?

The prevalence of e-learning systems and on-line courses has made educational material widely accessible to students of varying abilities and backgrounds. There is thus a growing need to accommodate for individual differences in e-learning systems. This paper presents an algorithm called EduRank for personalizing educational content to students that combines a collaborative filtering algorithm with voting methods. EduRank constructs a difficulty ranking for each student by aggregating the rankings of similar students using different aspects of their performance on common questions. These aspects include grades, number of retries, and time spent solving questions. It infers a difficulty ranking directly over the questions for each student, rather than ordering them according to the student's predicted score. The EduRank algorithm was tested on two data sets containing thousands of students and a million records. It was able to outperform the state-of-the-art ranking approaches as well as a domain expert. EduRank was used by students in a classroom activity, where a prior model was incorporated to predict the difficulty rankings of students with no prior history in the system. It was shown to lead students to solve more difficult questions than an ordering by a domain expert, without reducing their performance.

Are you a concerned citizen of the modern world? Do you ever worry that algorithms are stealing your data? Do you secretly have little idea what algorithms and data actually are? Then Hello World is for you. With refreshing simplicity, Fry explains what AI, machine learning and complicated algorithms really mean, providing some succinct explanations of the Cambridge Analytica scandal, driverless cars and many other unnerving modern phenomena.