Emily Chen

Shivam Shukla, Emily Chen, Manhaz Roshanaei et al.

There has been a growing research interest in Digital Therapeutic Alliance (DTA) as the field of AI-powered conversational agents are being deployed in mental health care, particularly those delivering CBT (Cognitive Behaviour Therapy). Our proposition argues that the current design paradigm which seeks to optimize the bond between a patient in need of support and an AI agent contains a subtle but consequential trap: it risks producing an "appearance of connection" that unintentionally disrupts the fundamental human need for relatedness, which potentially displaces the authentic human relationships upon which long-term psychological recovery depends. We propose a reorientation from designing artificial intelligence tools that simulate relationships to designing AI that scaffolds them. To operationalize our argument, we propose an interdisciplinary model that translates the Responsible AI Six Sphere Framework through the lens of Self-Determination Theory (SDT), with a specific focus on the basic psychological need for relatedness. The resulting model offers the technical and often clinical communities a set of relationship-centered design guidelines and relevant provocations for building AI systems that function not just as companions, but as a catalyst for strengthening a patient's entire relational ecology; their connections with therapists, caregivers, family, and peers. In doing so, we discuss a model towards a more sustainable ecosystem of relationship-centered AI in mental health care.

Emily Chen, Alexander J. Bisberg, Dmitri Williams et al.

This paper examines how player flexibility -- a player's willingness to engage in a breadth of options or specialize -- manifests across two gaming environments: League of Legends (League) and Teamfight Tactics (TFT). We analyze the gameplay decisions of 4,830 players who have played at least 50 competitive games in both titles and explore cross-game dynamics of behavior retention and consistency. Our work introduces a novel cross-game analysis that tracks the same players' behavior across two different environments, reducing self-selection bias. Our findings reveal that while games incentivize different behaviors (specialization in League versus flexibility in TFT) for performance-based success, players exhibit consistent behavior across platforms. This study contributes to long-standing debate about agency versus structure, showing individual agency may be more predictive of cross-platform behavior than game-imposed structure in competitive settings. These insights offer implications for game developers, designers and researchers interested in building systems to promote behavior change.

Hannah Zhou, Allison Chen, Celine Buer et al.

This paper presents a cost-effective, low-power approach to unintentional fall detection using knowledge distillation-based LSTM (Long Short-Term Memory) models to significantly improve accuracy. With a primary focus on analyzing time-series data collected from various sensors, the solution offers real-time detection capabilities, ensuring prompt and reliable identification of falls. The authors investigate fall detection models that are based on different sensors, comparing their accuracy rates and performance. Furthermore, they employ the technique of knowledge distillation to enhance the models' precision, resulting in refined accurate configurations that consume lower power. As a result, this proposed solution presents a compelling avenue for the development of energy-efficient fall detection systems for future advancements in this critical domain.

Emily Chen, Alexander Bisberg, Emilio Ferrara

This study investigates the concept of flexibility within League of Legends, a popular online multiplayer game, focusing on the relationship between user adaptability and team success. Utilizing a dataset encompassing players of varying skill levels and play styles, we calculate two measures of flexibility for each player: overall flexibility and temporal flexibility. Our findings suggest that the flexibility of a user is dependent upon a user's preferred play style, and flexibility does impact match outcome. This work also shows that skill level not only indicates how willing a player is to adapt their play style but also how their adaptability changes over time. This paper highlights the duality and balance of specialization versus flexibility, providing insights that can inform strategic planning, collaboration and resource allocation in competitive environments.

Jesse Zymet, Andy Luo, Swapnil Shinde et al.

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range of successes. Another approach discovers diverse attacks by combining crowdsourced harmful queries and tactics into instructions for the attacker, but does so at random, limiting effectiveness. This article introduces a novel framework, Adaptive Instruction Composition, that combines crowdsourced texts according to an adaptive mechanism trained to jointly optimize effectiveness with diversity. We use reinforcement learning to balance exploration with exploitation in a combinatorial space of instructions to guide the attacker toward diverse generations tailored to target vulnerabilities. We demonstrate that our approach substantially outperforms random combination on a set of effectiveness and diversity metrics, even under model transfer. Further, we show that it surpasses a host of recent adaptive approaches on Harmbench. We employ a lightweight neural contextual bandit that adapts to contrastive embedding inputs, and provide ablations suggesting that the contrastive pretraining enables the network to rapidly generalize and scale to the massive space as it learns.

Shayne Longpre, Christopher Akiki, Campbell Lund et al.

Since 2019, the Hugging Face Model Hub has been the primary global platform for sharing open weight AI models. By releasing a dataset of the complete history of weekly model downloads (June 2020-August 2025) alongside model metadata, we provide the most rigorous examination to-date of concentration dynamics and evolving characteristics in the open model economy. Our analysis spans 851,000 models, over 200 aggregated attributes per model, and 2.2B downloads. We document a fundamental rebalancing of economic power: US open-weight industry dominance by Google, Meta, and OpenAI has declined sharply in favor of unaffiliated developers, community organizations, and, as of 2025, Chinese industry, with DeepSeek and Qwen models potentially heralding a new consolidation of market power. We identify statistically significant shifts in model properties, a 17X increase in average model size, rapid growth in multimodal generation (3.4X), quantization (5X), and mixture-of-experts architectures (7X), alongside concerning declines in data transparency, with open weights models surpassing truly open source models for the first time in 2025. We expose a new layer of developer intermediaries that has emerged, focused on quantizing and adapting base models for both efficiency and artistic expression. To enable continued research and oversight, we release the complete dataset with an interactive dashboard for real-time monitoring of concentration dynamics and evolving properties in the open model economy.

Alberto Purpura, Emily Chen, Swapnil Shinde

Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to assist in the review process of marketing content, making sure they comply with a given list of requirements. The contributions of this paper are the following: (i) we present a novel approach -- that does not rely on any external knowledge representation -- for the automatic identification of compliance issues in textual content; (ii) compare the effectiveness of different fine-tuning strategies like Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) in training models to solve this problem; (iii) we evaluate the effectiveness of training small LLMs to generate reasoning tokens before providing their final response; (iv) we evaluate how the choice and combinations of different reward functions affects the performance of a model trained with GRPO.

Orlando Marquez Ayala, Patrice Bechard, Emily Chen et al.

Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results, fine-tuning improves quality by 10% on average. We also perform systematic error analysis to reveal model limitations.

Patrice Bechard, Orlando Marquez Ayala, Emily Chen et al.

There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Yet, it remains unclear whether such complex agentic systems are necessary given their cost and operational overhead. We argue that a coding agent equipped only with a terminal and a filesystem can solve many enterprise tasks more effectively by interacting directly with platform APIs. We evaluate this hypothesis across diverse real-world systems and show that these low-level terminal agents match or outperform more complex agent architectures. Our findings suggest that simple programmatic interfaces, combined with strong foundation models, are sufficient for practical enterprise automation.

Melissa Kazemi Rad, Alberto Purpura, Himanshu Kumar et al.

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) generation of geometrically controlled examples using a constrained LLM, and (ii) augmentation through a multi-agentic reflective process that promotes stylistic diversity and uncovers edge cases. This combination enables both reliable coverage of the input space and nuanced exploration of harmful content. Using two benchmark data sets, we demonstrate that augmenting a harmful text classification dataset with GRAID leads to significant improvements in downstream guardrail model performance.

Emily Chen, Nicholas Huang, Casey Robinson et al.

This paper explores null elements in English, Chinese, and Korean Penn treebanks. Null elements contain important syntactic and semantic information, yet they have typically been treated as entities to be removed during language processing tasks, particularly in constituency parsing. Thus, we work towards the removal and, in particular, the restoration of null elements in parse trees. We focus on expanding a rule-based approach utilizing linguistic context information to Chinese, as rule based approaches have historically only been applied to English. We also worked to conduct neural experiments with a language agnostic sequence-to-sequence model to recover null elements for English (PTB), Chinese (CTB) and Korean (KTB). To the best of the authors' knowledge, null elements in three different languages have been explored and compared for the first time. In expanding a rule based approach to Chinese, we achieved an overall F1 score of 80.00, which is comparable to past results in the CTB. In our neural experiments we achieved F1 scores up to 90.94, 85.38 and 88.79 for English, Chinese, and Korean respectively with functional labels.

Lane Schwartz, Emily Chen, Hyunji Hayley Park et al.

St. Lawrence Island Yupik (ISO 639-3: ess) is an endangered polysynthetic language in the Inuit-Yupik language family indigenous to Alaska and Chukotka. This work presents a step-by-step pipeline for the digitization of written texts, and the first publicly available digital corpus for St. Lawrence Island Yupik, created using that pipeline. This corpus has great potential for future linguistic inquiry and research in NLP. It was also developed for use in Yupik language education and revitalization, with a primary goal of enabling easy access to Yupik texts by educators and by members of the Yupik community. A secondary goal is to support development of language technology such as spell-checkers, text-completion systems, interactive e-books, and language learning apps for use by the Yupik community.

Isaac Lage, Emily Chen, Jeffrey He et al.

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable under three specific tasks that users may perform with machine learning systems: simulation of the response, verification of a suggested response, and determining whether the correctness of a suggested response changes under a change to the inputs. Through carefully controlled human-subject experiments, we identify regularizers that can be used to optimize for the interpretability of machine learning systems. Our results show that the type of complexity matters: cognitive chunks (newly defined concepts) affect performance more than variable repetitions, and these trends are consistent across tasks and domains. This suggests that there may exist some common design principles for explanation systems.

Menaka Narayanan, Emily Chen, Jeffrey He et al.

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable in the specific context of verification. Suppose we have a machine learning system that predicts X, and we provide rationale for this prediction X. Given an input, an explanation, and an output, is the output consistent with the input and the supposed rationale? Via a series of user-studies, we identify what kinds of increases in complexity have the greatest effect on the time it takes for humans to verify the rationale, and which seem relatively insensitive.

Daniel S. Katz, Kyle E. Niemeyer, Sandra Gesing et al.

This report records and discusses the Fourth Workshop on Sustainable Software for Science: Practice and Experiences (WSSSPE4). The report includes a description of the keynote presentation of the workshop, the mission and vision statements that were drafted at the workshop and finalized shortly after it, a set of idea papers, position papers, experience papers, demos, and lightning talks, and a panel discussion. The main part of the report covers the set of working groups that formed during the meeting, and for each, discusses the participants, the objective and goal, and how the objective can be reached, along with contact information for readers who may want to join the group. Finally, we present results from a survey of the workshop attendees.