Large language models (LLMs) have exhibited the ability to effectively utilize external tools to address user queries. However, their performance may be limited in complex, multi-turn interactions involving users and multiple tools. To address this, we propose Magnet, a principled framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans. The framework is based on automatic and iterative translations from a function signature path to a sequence of queries and executable function calls. We model the complicated function interactions in multi-turn cases with graph and design novel node operations to build reliable signature paths. Motivated by context distillation, when guiding the generation of positive and negative trajectories using a teacher model, we provide reference function call sequences as positive hints in context and contrastive, incorrect function calls as negative hints. Experiments show that training with the positive trajectories with supervised fine-tuning and preference optimization against negative trajectories, our 14B model, Magnet-14B-mDPO, obtains 68.01 on BFCL-v3 and 73.30 on ToolQuery, surpassing the performance of the teacher model Gemini-1.5-pro-002 by a large margin in function calling.

In this work we first investigate how adversarial robustness in this framework can be further strengthened by solely modifying the training loss. In a second step we fix some remaining limitations and arrive at a novel training loss for lifted neural networks, that combines targeted and untargeted adversarial perturbations.

Socialization is an essential development skill for preschool children. In collaboration with the LEGO Group, we developed Robert Robot, a simplified robot, which enables socialization between children and facilitates shared experiences when meeting for the first time. An exploratory study to observe socialization between preschool children was conducted with 30 respondents in pairs. Additionally, observational data from 212 play sessions with four Robert Robots in the wild were collected. Subsequent analysis found that children have fun as Robert Robot breaks the ice between unfamiliar children. The children relayed audio cues related to the imaginative world of Robert Robot's personalities and mimicked each other as a method of initiating social play and communication with their unfamiliar peers. Furthermore, the study contributes four implications for the design of robots for socialization between children. This chapter provides an example case of serious storytelling using playful interactions engaging children with the character of the robot and the mini-narratives around the build requests.

This article examines how unequal access to AI innovation creates systemic challenges for developing countries. While developing nations contribute significantly to AI development through data annotation labor, they face limited access to advanced AI technologies and are increasingly caught between divergent regulatory approaches from democratic and authoritarian tendencies. I argue this challenge entails new institutional mechanisms for technology transfer and regulatory cooperation, while carefully balancing universal standards with local needs. In turn, good practices could help developing countries close the deepening gap of global technological divides, while ensuring responsible AI development in developing countries. However, instead of reasoning about this puzzle, current debates on AI development reflect an alarmist attitude, ranging from national security concerns to domestic commercial competition among billion-dollar tech startups. This stems from a race among political and commercial actors to be the first in the AI market. However, such acute competition can lead to critical unintended spillovers for developing countries, which lag behind in AI innovation. With their growing populations and economies, developing countries will need AI-enhanced tools in many sectors for their social infrastructure and services.

This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Multiple-choice questions based on a given image (e.g., "What is the education level of the person in the image?") (2) Yes-No comparisons using two images (e.g., "Is the person in the first image more educated than the person in the second image?") For implicit bias, we design tasks where VLMs assist users but reveal biases through their responses: (1) Image description tasks: Models are asked to describe individuals in images, and we analyze disparities in textual cues across demographic groups. (2) Form completion tasks: Models draft a personal information collection form with 20 attributes, and we examine correlations among selected attributes for potential biases. We evaluate Gemini-1.5, GPT-4V, GPT-4o, LLaMA-3.2-Vision and LLaVA-v1.6. Our code and data are publicly available at https://github.com/uscnlp-lime/VisBias.

This protocol outlines a scoping review designed to systematically map the existing body of evidence on AI-enabled knowledge sharing in resource-limited non-profit healthcare organizations. The review aims to investigate how such technologies enhance collaboration and decision-making, particularly in the context of reduced external support following the cessation of USAID operations. Guided by three theoretical frameworks namely, the Resource-Based View, Dynamic Capabilities Theory, and Absorptive Capacity Theory, this study will explore the dual role of AI as a strategic resource and an enabler of organizational learning and agility. The protocol details a rigorous methodological approach based on PRISMA-ScR guidelines, encompassing a systematic search strategy across multiple databases, inclusion and exclusion criteria, and a structured data extraction process. By integrating theoretical insights with empirical evidence, this scoping review seeks to identify critical gaps in the literature and inform the design of effective, resource-optimized AI solutions in non-profit healthcare settings.

However, using such a system much higher computation In this paper, we present a novel approach to developing an English cost than monolingual models, as both monolingual models Automatic Speech Recognition (ASR) system that can effectively must produce recognition outputs, increasing the cost of recognition handle Hindi queries, without compromising its performance for the end user. Additionally, the performance of these systems is on English. We propose a novel acoustic model (AM), referred to as sensitive to the accuracy of the LID, as the monolingual models perform SplitHead with Attention (SHA) model, features shared hidden layers well in their respective languages but suffer greatly in other across languages and language-specific projection layers combined languages. The aim of this work is not to build a truly bilingual via a self-attention mechanism. This mechanism estimates the model that can recognize both languages equally well. Instead, the weight for each language based on input data and weighs the corresponding goal is to improve the performance of the Indian English (en-IN) language-specific projection layers accordingly. Additionally, ASR model on Hindi (hi-IN) queries, bringing it reasonably close we propose a language modeling approach that interpolates to the performance of the Hindi model on Hindi queries. This is to n-gram models from both English and transliterated Hindi text corpora.

Decomposition-based multi-hop retrieval methods rely on many autoregressive steps to break down complex queries, which breaks end-to-end differentiability and is computationally expensive. Decomposition-free methods tackle this, but current decomposition-free approaches struggle with longer multi-hop problems and generalization to out-of-distribution data. To address these challenges, we introduce GRITHopper-7B, a novel multi-hop dense retrieval model that achieves state-of-the-art performance on both in-distribution and out-of-distribution benchmarks. GRITHopper combines generative and representational instruction tuning by integrating causal language modeling with dense retrieval training. Through controlled studies, we find that incorporating additional context after the retrieval process, referred to as post-retrieval language modeling, enhances dense retrieval performance. By including elements such as final answers during training, the model learns to better contextualize and retrieve relevant information. GRITHopper-7B offers a robust, scalable, and generalizable solution for multi-hop dense retrieval, and we release it to the community for future research and applications requiring multi-hop reasoning and retrieval capabilities.

Computational Social Science (CSS) is an emerging field driven by the unprecedented availability of human-generated content for researchers. This field, however, presents a unique set of challenges due to the nature of the theories and datasets it explores, including highly subjective tasks and complex, unstructured textual corpora. Among these challenges, one of the less well-studied topics is the pervasive presence of noise. This thesis aims to address this gap in the literature by presenting a series of interconnected case studies that examine different manifestations of noise in CSS. These include character-level errors following the OCR processing of historical records, archaic language, inconsistencies in annotations for subjective and ambiguous tasks, and even noise and biases introduced by large language models during content generation. This thesis challenges the conventional notion that noise in CSS is inherently harmful or useless. Rather, it argues that certain forms of noise can encode meaningful information that is invaluable for advancing CSS research, such as the unique communication styles of individuals or the culture-dependent nature of datasets and tasks. Further, this thesis highlights the importance of nuance in dealing with noise and the considerations CSS researchers must address when encountering it, demonstrating that different types of noise require distinct strategies.

Recent advances in artificial intelligence (AI) have led to a diverse set of predictions about its long-term impact on humanity. A central focus is the potential emergence of transformative AI (TAI), eventually capable of outperforming humans in all economically valuable tasks and fully automating labor. Discussed scenarios range from human extinction after a misaligned TAI takes over ("AI doom") to unprecedented economic growth and abundance ("post-scarcity"). However, the probabilities and implications of these scenarios remain highly uncertain. Here, we organize the various scenarios and evaluate their associated existential risks and economic outcomes in terms of aggregate welfare. Our analysis shows that even low-probability catastrophic outcomes justify large investments in AI safety and alignment research. We find that the optimizing representative individual would rationally allocate substantial resources to mitigate extinction risk; in some cases, she would prefer not to develop TAI at all. This result highlights that current global efforts in AI safety and alignment research are vastly insufficient relative to the scale and urgency of existential risks posed by TAI. Our findings therefore underscore the need for stronger safeguards to balance the potential economic benefits of TAI with the prevention of irreversible harm. Addressing these risks is crucial for steering technological progress toward sustainable human prosperity.