To benchmark a model's long-form factuality in open domains, we first use GPT -4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE).

Connecticut man falls victim to fake crypto investment company promising $368,000 returns, loses life savings in wire transfer scam that the FBI says is nearly impossible to recover.

This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We conduct a literature search via Scopus and Google Scholar, examining over 2,000 publications. We assess publications against four inclusion and four exclusion criteria related to their language, research focus, publication year, and type. Eventually, we select 103 studies. We classify these studies into semantic categories and topics to provide a comprehensive overview of the field, including the tasks performed by LLMs, the architectures of LLMs, the existing datasets specifically designed for evaluating LLMs in CO, and the field of application. Finally, we identify future directions for leveraging LLMs in this field.

On a recent commute to work, I texted my distant family about our fantasy baseball league, which was nice because I felt connected to them for a second. Then I switched apps and became enraged by a stupid opinion I saw on X, which I shouldn't be using anymore due to its advanced toxicity and mind-numbing inanity. Many minutes passed before I was able to stop reading the stupid replies to the stupid original post and relax the muscles of my face. This is the duality of the phone: It connects me to my loved ones, and sometimes I think it's ruining my life. I need it and I want it, but sometimes I hate it and I fear it.

We extend the existing work on Hopfield network state classification, employing more complex models that remain interpretable, such as densely-connected feed-forward deep neural networks and support vector machines. The states of the Hopfield network can be grouped into several classes, including learned (those presented during training), spurious (stable states that were not learned), and prototype (stable states that were not learned but are representative for a subset of learned states). It is often useful to determine to what class a given state belongs to; for example to ignore spurious states when retrieving from the network. Previous research has approached the state classification task with simple linear methods, most notably the stability ratio. We deepen the research on classifying states from prototype-regime Hopfield networks, investigating how varying the factors strengthening prototypes influences the state classification task. We study the generalizability of different classification models when trained on states derived from different prototype tasks -- for example, can a network trained on a Hopfield network with 10 prototypes classify states from a network with 20 prototypes? We find that simple models often outperform the stability ratio while remaining interpretable. These models require surprisingly little training data and generalize exceptionally well to states generated by a range of Hopfield networks, even those that were trained on exceedingly different datasets.

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with feed-forward networks, enabling a more expressive representation of relationships between tokens. This approach modifies only the attention matrix calculation while preserving the matrix dimensions, making it easily adaptable to existing transformer-based architectures. We provide a detailed mathematical justification for why Neural Attention increases representational capacity and conduct controlled experiments to validate this claim. When comparing Neural Attention and Dot-Product Attention, NLP experiments on WikiText-103 show a reduction in perplexity of over 5 percent. Similarly, experiments on CIFAR-10 and CIFAR-100 show comparable improvements for image classification tasks. While Neural Attention introduces higher computational demands, we develop techniques to mitigate these challenges, ensuring practical usability without sacrificing the increased expressivity it provides. This work establishes Neural Attention as an effective means of enhancing the predictive capabilities of transformer models across a variety of applications.

We present DreamLLM-3D, a composite multimodal AI system behind an immersive art installation for dream re-experiencing. It enables automated dream content analysis for immersive dream-reliving, by integrating a Large Language Model (LLM) with text-to-3D Generative AI. The LLM processes voiced dream reports to identify key dream entities (characters and objects), social interaction, and dream sentiment. The extracted entities are visualized as dynamic 3D point clouds, with emotional data influencing the color and soundscapes of the virtual dream environment. Additionally, we propose an experiential AI-Dreamworker Hybrid paradigm. Our system and paradigm could potentially facilitate a more emotionally engaging dream-reliving experience, enhancing personal insights and creativity.

While LLMs have exhibited strong performance on various NLP tasks, it is noteworthy that most of these tasks rely on utilizing the vast amount of knowledge encoded in LLMs' parameters, rather than solving new problems without prior knowledge. In cognitive research, the latter ability is referred to as fluid intelligence, which is considered to be critical for assessing human intelligence. Recent research on fluid intelligence assessments has highlighted significant deficiencies in LLMs' abilities. In this paper, we analyze the challenges LLMs face in demonstrating fluid intelligence through controlled experiments, using the most representative ARC task as an example. Our study revealed three major limitations in existing LLMs: limited ability for skill composition, unfamiliarity with abstract input formats, and the intrinsic deficiency of left-to-right decoding. Our data and code can be found in https://wujunjie1998.github.io/araoc-benchmark.github.io/.

Cities are at the forefront of addressing global sustainability challenges, particularly those exacerbated by climate change. Traditional zoning codes, which often segregate land uses, have been linked to increased vehicular dependence, urban sprawl, and social disconnection, undermining broader social and environmental sustainability objectives. This study investigates the adoption and impact of form-based codes (FBCs), which aim to promote sustainable, compact, and mixed-use urban forms as a solution to these issues. Using Natural Language Processing (NLP) techniques, we analyzed zoning documents from over 2000 U.S. census-designated places to identify linguistic patterns indicative of FBC principles. Our findings reveal widespread adoption of FBCs across the country, with notable variations within regions. FBCs are associated with higher floor-to-area ratios, narrower and more consistent street setbacks, and smaller plots. We also find that places with FBCs have improved walkability, shorter commutes, and a higher share of multi-family housing. Our findings highlight the utility of NLP for evaluating zoning codes and underscore the potential benefits of form-based zoning reforms for enhancing urban sustainability.