In an era where artificial intelligence and machine learning algorithms increasingly impact human life, it is crucial to develop models that account for potential discrimination in their predictions. This paper tackles this problem by introducing a new classification tree algorithm using a novel splitting criterion that incorporates fairness adjustments into the tree-building process. The proposed method integrates a fairness-aware impurity measure that balances predictive accuracy with fairness across protected groups. By ensuring that each splitting node considers both the gain in classification error and the fairness, our algorithm encourages splits that mitigate discrimination. Importantly, in penalizing unfair splits, we account for the uncertainty in the fairness metric by utilizing its confidence interval instead of relying on its point estimate. Experimental results on benchmark and synthetic datasets illustrate that our method effectively reduces discriminatory predictions compared to traditional classification trees, without significant loss in overall accuracy.

This paper presents the predictive coding network (PCN), a convolutional architecture with local recurrent and feedback connections. Higher layers provide top-down predictions while the lower layers provide the prediction errors, which are refined over time by the local recurrence. This idea is not new, other work (such as that of Lotter et al. and others) have used this for other tasks, such as video prediction and object recognition, though this has yet to be shown to scale to larger scale tasks such as ImageNet. The authors compare the performance of PCN, with varying number of cycles of recurrent processing, to standard CNN architectures on multiple image datasets. In general, PCN has slightly lower error than standard architectures with a comparable number of parameters.

Climate change communication on social media increasingly employs microtargeting strategies to effectively reach and influence specific demographic groups. This study presents a post-hoc analysis of microtargeting practices within climate campaigns by leveraging large language models (LLMs) to examine Facebook advertisements. Our analysis focuses on two key aspects: demographic targeting and fairness. We evaluate the ability of LLMs to accurately predict the intended demographic targets, such as gender and age group, achieving an overall accuracy of 88.55%. Furthermore, we instruct the LLMs to generate explanations for their classifications, providing transparent reasoning behind each decision. These explanations reveal the specific thematic elements used to engage different demographic segments, highlighting distinct strategies tailored to various audiences. Our findings show that young adults are primarily targeted through messages emphasizing activism and environmental consciousness, while women are engaged through themes related to caregiving roles and social advocacy. In addition to evaluating the effectiveness of LLMs in detecting microtargeted messaging, we conduct a comprehensive fairness analysis to identify potential biases in model predictions. Our findings indicate that while LLMs perform well overall, certain biases exist, particularly in the classification of senior citizens and male audiences. By showcasing the efficacy of LLMs in dissecting and explaining targeted communication strategies and by highlighting fairness concerns, this study provides a valuable framework for future research aimed at enhancing transparency, accountability, and inclusivity in social media-driven climate campaigns.

The rapid expansion of records creates significant challenges in management, including retention and disposition, appraisal, and organization. Our study underscores the benefits of integrating artificial intelligence (AI) within the broad realm of archival science. In this work, we start by performing a thorough analysis to understand the current use of AI in this area and identify the techniques employed to address challenges. Subsequently, we document the results of our review according to specific criteria. Our findings highlight key AI driven strategies that promise to streamline record-keeping processes and enhance data retrieval efficiency. We also demonstrate our review process to ensure transparency regarding our methodology. Furthermore, this review not only outlines the current state of AI in archival science and records management but also lays the groundwork for integrating new techniques to transform archival practices. Our research emphasizes the necessity for enhanced collaboration between the disciplines of artificial intelligence and archival science.

In recent years, there has been significant effort to align large language models with human preferences. This work focuses on developing a chatbot specialized in the real estate domain, with an emphasis on incorporating compliant behavior to ensure it can be used without perpetuating discriminatory practices like steering and redlining, which have historically plagued the real estate industry in the United States. Building on prior work, we present a method for generating a synthetic general instruction-following dataset, along with safety data. Through extensive evaluations and benchmarks, we fine-tuned a llama-3-8B-instruct model and demonstrated that we can enhance it's performance significantly to match huge closed-source models like GPT-4o while making it safer and more compliant. We open-source the model, data and code to support further development and research in the community.

How are we able to learn about complex current events just from short snippets of video? While natural language enables straightforward ways to represent under-specified, partially observable events, visual data does not facilitate analogous methods and, consequently, introduces unique challenges in event understanding. With the growing prevalence of vision-capable AI agents, these systems must be able to model events from collections of unstructured video data. To tackle robust event modeling in multimodal settings, we introduce a multimodal formulation for partially-defined events and cast the extraction of these events as a three-stage span retrieval task. We propose a corresponding benchmark for this task, MultiVENT-G, that consists of 14.5 hours of densely annotated current event videos and 1,168 text documents, containing 22.8K labeled event-centric entities. We propose a collection of LLM-driven approaches to the task of multimodal event analysis, and evaluate them on MultiVENT-G. Results illustrate the challenges that abstract event understanding poses and demonstrates promise in event-centric video-language systems.

The performance of Large Language Models (LLMs) is substantially influenced by the pretraining corpus, which consists of vast quantities of unsupervised data processed by the models. Despite its critical role in model performance, ensuring the quality of this data is challenging due to its sheer volume and the absence of sample-level quality annotations and enhancements. In this paper, we introduce DecorateLM, a data engineering method designed to refine the pretraining corpus through data rating, tagging and editing. Specifically, DecorateLM rates texts against quality criteria, tags texts with hierarchical labels, and edits texts into a more formalized format. Due to the massive size of the pretraining corpus, adopting an LLM for decorating the entire corpus is less efficient. Therefore, to balance performance with efficiency, we curate a meticulously annotated training corpus for DecorateLM using a large language model and distill data engineering expertise into a compact 1.2 billion parameter small language model (SLM). We then apply DecorateLM to enhance 100 billion tokens of the training corpus, selecting 45 billion tokens that exemplify high quality and diversity for the further training of another 1.2 billion parameter LLM. Our results demonstrate that employing such high-quality data can significantly boost model performance, showcasing a powerful approach to enhance the quality of the pretraining corpus.

We demonstrate that when people use large language models (LLMs) to generate recommendations, the LLMs produce responses that reflect both what the user wants and who the user is. While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of whether the user revealed their identity intentionally through explicit indications or unintentionally through implicit cues. We argue that chatbots ought to transparently indicate when recommendations are influenced by a user's revealed identity characteristics, but observe that they currently fail to do so. Our experiments show that even though a user's revealed identity significantly influences model recommendations (p < 0.001), model responses obfuscate this fact in response to user queries. This bias and lack of transparency occurs consistently across multiple popular consumer LLMs (gpt-4o-mini, gpt-4-turbo, llama-3-70B, and claude-3.5) and for four American racial groups.

The widespread presence of hate speech on the internet, including formats such as text-based tweets and vision-language memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored to specific modalities; however, there is a notable gap in transferring detection capabilities across different formats. This study conducts extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. Our findings demonstrate that text-based hate speech examples can significantly enhance the classification accuracy of vision-language hate speech. Moreover, text-based demonstrations outperform vision-language demonstrations in few-shot learning settings. These results highlight the effectiveness of cross-modality knowledge transfer and offer valuable insights for improving hate speech detection systems.

When acting as a privacy-enhancing technology, synthetic data generation (SDG) aims to maintain a resemblance to the real data while excluding personally-identifiable information. Many SDG algorithms provide robust differential privacy (DP) guarantees to this end. However, we show that the strongest class of SDG algorithms--those that preserve \textit{marginal probabilities}, or similar statistics, from the underlying data--leak information about individuals that can be recovered more efficiently than previously understood. We demonstrate this by presenting a novel membership inference attack, MAMA-MIA, and evaluate it against three seminal DP SDG algorithms: MST, PrivBayes, and Private-GSD. MAMA-MIA leverages knowledge of which SDG algorithm was used, allowing it to learn information about the hidden data more accurately, and orders-of-magnitude faster, than other leading attacks. We use MAMA-MIA to lend insight into existing SDG vulnerabilities. Our approach went on to win the first SNAKE (SaNitization Algorithm under attacK ... $\varepsilon$) competition.