Keyword mnemonics are memorable explanations that link new terms to simpler keywords. Prior works generate mnemonics for students, but they do not guide models toward mnemonics students prefer and aid learning. We build SMART, a mnemonic generator trained on feedback from real students learning new terms. To train SMART, we first fine-tune LLaMA-2 on a curated set of user-written mnemonics. We then use LLM alignment to enhance SMART: we deploy mnemonics generated by SMART in a flashcard app to find preferences on mnemonics students favor. We gather 2684 preferences from 45 students across two types: expressed (inferred from ratings) and observed (inferred from student learning), yielding three key findings. First, expressed and observed preferences disagree; what students think is helpful does not fully capture what is truly helpful. Second, Bayesian models can synthesize complementary data from multiple preference types into a single effectiveness signal. SMART is tuned via Direct Preference Optimization on this signal, which we show resolves ties and missing labels in the typical method of pairwise comparisons, augmenting data for LLM output quality gains. Third, mnemonic experts assess SMART as matching GPT-4, at much lower deployment costs, showing the utility of capturing diverse student feedback to align LLMs in education.

Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate [1-4], lack common sense [5], and are biased [6, 7]--shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here we present a hybrid collective intelligence system that mitigates these risks by leveraging the complementary strengths of human experience and the vast information processed by LLMs. We show that hybrid collectives of physicians and LLMs outperform both single physicians and physician collectives, as well as single LLMs and LLM ensembles. This result holds across a range of medical specialties and professional experience, and can be attributed to humans' and LLMs' complementary contributions that lead to different kinds of errors. Our approach highlights the potential for collective human and machine intelligence to improve accuracy in complex, open-ended domains [8] like medical diagnostics. Diagnostic errors are among the most pressing issues in medical practice [9-11], causing an estimated 795,000 deaths and permanent disabilities in the United States alone each year [12]. Reducing diagnostic errors--without incurring substantially higher costs--is essential to improve patient outcomes worldwide. This challenge has motivated a recent surge in diagnostic technologies exploiting artificial intelligence (AI) to interpret medical records, tests, and images [13, 14]. Deep learning approaches in medical imaging have shown great promise. Notable examples include mammography interpretation, cardiac function assessment, and lung cancer screening, some of which have progressed beyond the testing phase and entered clinical practice [15-17]. Recent years have also witnessed the rise of AI foundation models, especially LLMs, which show remarkable abilities to process natural language, providing accurate answers to questions in almost any domain, including medicine [18-21]. However, a recent meta-analysis [22] found that physicians often outperform LLMs, and that LLMs differ vastly in performance, also between medical specialties.

Vehicle Routing Problems (VRPs) are optimization problems with significant real-world implications in logistics, transportation, and supply chain management. Despite the recent progress made in learning to solve individual VRP variants, there is a lack of a unified approach that can effectively tackle a wide range of tasks, which is crucial for real-world impact. This paper introduces RouteFinder, a framework for developing foundation models for VRPs. Our key idea is that a foundation model for VRPs should be able to model variants by treating each variant as a subset of a larger VRP problem, equipped with different attributes. We introduce a parallelized environment that can handle any combination of attributes at the same time in a batched manner, and an efficient sampling procedure to train on a mix of problems at each optimization step that can greatly improve convergence robustness. We also introduce novel Global Feature Embeddings that project instance-wise attributes efficiently onto the latent space and help the model understand different VRP variants. Finally, we introduce Efficient Adapter Layers, a simple yet effective technique to finetune pre-trained RouteFinder models to solve novel variants with previously unseen attributes outside of the original feature space.

In recent years, generated content in music has gained significant popularity, with large language models being effectively utilized to produce human-like lyrics in various styles, themes, and linguistic structures. This technological advancement supports artists in their creative processes but also raises issues of authorship infringement, consumer satisfaction and content spamming. To address these challenges, methods for detecting generated lyrics are necessary. However, existing works have not yet focused on this specific modality or on creative text in general regarding machine-generated content detection methods and datasets. In response, we have curated the first dataset of high-quality synthetic lyrics and conducted a comprehensive quantitative evaluation of various few-shot content detection approaches, testing their generalization capabilities and complementing this with a human evaluation. Our best few-shot detector, based on LLM2Vec, surpasses stylistic and statistical methods, which are shown competitive in other domains at distinguishing human-written from machine-generated content. It also shows good generalization capabilities to new artists and models, and effectively detects post-generation paraphrasing. This study emphasizes the need for further research on creative content detection, particularly in terms of generalization and scalability with larger song catalogs. All datasets, pre-processing scripts, and code are available publicly on GitHub and Hugging Face under the Apache 2.0 license.

LLM-based agents have emerged as promising tools, which are crafted to fulfill complex tasks by iterative planning and action. However, these agents are susceptible to undesired planning hallucinations when lacking specific knowledge for expertise-intensive tasks. To address this, preliminary attempts are made to enhance planning reliability by incorporating external workflow-related knowledge. Despite the promise, such infused knowledge is mostly disorganized and diverse in formats, lacking rigorous formalization and comprehensive comparisons. Motivated by this, we formalize different formats of workflow knowledge and present FlowBench, the first benchmark for workflow-guided planning. FlowBench covers 51 different scenarios from 6 domains, with knowledge presented in diverse formats. To assess different LLMs on FlowBench, we design a multi-tiered evaluation framework. We evaluate the efficacy of workflow knowledge across multiple formats, and the results indicate that current LLM agents need considerable improvements for satisfactory planning. We hope that our challenging benchmark can pave the way for future agent planning research.

Large language models (LLMs) have attracted significant attention for their remarkable abilities in various natural language processing tasks, but they suffer from hallucinations that will cause performance degradation. One promising solution to improve the LLMs' performance is to ask LLMs to revise their answer after generation, a technique known as self-correction. Among the two types of self-correction, intrinsic self-correction is considered a promising direction because it does not utilize external knowledge. However, recent works doubt the validity of LLM's ability to conduct intrinsic self-correction. In this paper, we present a novel perspective on the intrinsic self-correction capabilities of LLMs through theoretical analyses and empirical experiments. In addition, we identify two critical factors for successful self-correction: zero temperature and fair prompts. Leveraging these factors, we demonstrate that intrinsic self-correction ability is exhibited across multiple existing LLMs. Our findings offer insights into the fundamental theories underlying the self-correction behavior of LLMs and remark on the importance of unbiased prompts and zero temperature settings in harnessing their full potential.

Large Language Models (LLMs) like ChatGPT or Bard have revolutionized information retrieval and captivated the audience with their ability to generate custom responses in record time, regardless of the topic. In this article, we assess the capabilities of various LLMs in producing reliable, comprehensive, and sufficiently relevant responses about historical facts in French. To achieve this, we constructed a testbed comprising numerous history-related questions of varying types, themes, and levels of difficulty. Our evaluation of responses from ten selected LLMs reveals numerous shortcomings in both substance and form. Beyond an overall insufficient accuracy rate, we highlight uneven treatment of the French language, as well as issues related to verbosity and inconsistency in the responses provided by LLMs.

Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of joint training makes the optimization procedure extremely challenging. Data mixing methods partially address this problem, albeit having a sub-optimal performance across data sources and require multiple expensive training runs. In this paper, we propose a simple and efficient alternative for better optimization of the data sources by combining models individually trained on each data source with the base model using basic element-wise vector operations. The resulting model, namely Distribution Edited Model (DEM), is 11x cheaper than standard data mixing and outperforms strong baselines on a variety of benchmarks, yielding up to 6.2% improvement on MMLU, 11.5% on BBH, 16.1% on DROP, and 9.3% on HELM with models of size 3B to 13B. Notably, DEM does not require full re-training when modifying a single data-source, thus making it very flexible and scalable for training with diverse data sources.

The rapid research and development of generative artificial intelligence has enabled the generation of high-quality images, text, and 3D models from text prompts. This advancement impels an inquiry into whether these models can be leveraged to create digital artifacts for both creative and engineering applications. Drawing on innovative designs from other domains may be one answer to this question, much like the historical practice of ``bionics", where humans have sought inspiration from nature's exemplary designs. This raises the intriguing possibility of using generative models to simultaneously tackle design tasks across multiple domains, facilitating cross-domain learning and resulting in a series of innovative design solutions. In this paper, we propose LLM2FEA as the first attempt to discover novel designs in generative models by transferring knowledge across multiple domains. By utilizing a multi-factorial evolutionary algorithm (MFEA) to drive a large language model, LLM2FEA integrates knowledge from various fields to generate prompts that guide the generative model in discovering novel and practical objects. Experimental results in the context of 3D aerodynamic design verify the discovery capabilities of the proposed LLM2FEA. The designs generated by LLM2FEA not only satisfy practicality requirements to a certain degree but also feature novel and aesthetically pleasing shapes, demonstrating the potential applications of LLM2FEA in discovery tasks.

Large Language Models (LLMs) have significantly advanced user-bot interactions, enabling more complex and coherent dialogues. However, the prevalent text-only modality might not fully exploit the potential for effective user engagement. This paper explores the impact of multi-modal interactions, which incorporate images and audio alongside text, on user engagement in chatbot conversations. We conduct a comprehensive analysis using a diverse set of chatbots and real-user interaction data, employing metrics such as retention rate and conversation length to evaluate user engagement. Our findings reveal a significant enhancement in user engagement with multi-modal interactions compared to text-only dialogues. Notably, the incorporation of a third modality significantly amplifies engagement beyond the benefits observed with just two modalities. These results suggest that multi-modal interactions optimize cognitive processing and facilitate richer information comprehension. This study underscores the importance of multi-modality in chatbot design, offering valuable insights for creating more engaging and immersive AI communication experiences and informing the broader AI community about the benefits of multi-modal interactions in enhancing user engagement.