Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average . Pluralistic alignment instead seeks to capture diverse user preferences across a set of attributes, moving beyond just helpfulness and harmlessness. Toward this end, we propose a steerable pluralistic model based on few-shot comparative regression that can adapt to individual user preferences. Our approach leverages in-context learning and reasoning, grounded in a set of fine-grained attributes, to compare response options and make aligned choices. To evaluate our algorithm, we also propose two new steerable pluralistic benchmarks by adapting the Moral Integrity Corpus (MIC) and the HelpSteer2 datasets, demonstrating the applicability of our approach to value-aligned decision-making and reward modeling, respectively. Our few-shot comparative regression approach is interpretable and compatible with different attributes and LLMs, while outperforming multiple baseline and state-of-the-art methods. Our work provides new insights and research directions in pluralistic alignment, enabling a more fair and representative use of LLMs and advancing the state-of-the-art in ethical AI.

Large language models (LLMs) have the potential to address social and behavioral determinants of health by transforming labor intensive workflows in resource-constrained settings. Creating LLM-based applications that serve the needs of underserved communities requires a deep understanding of their local context, but it is often the case that neither LLMs nor their developers possess this local expertise, and the experts in these communities often face severe time/resource constraints. This creates a disconnect: how can one engage in meaningful co-design of an LLM-based application for an under-resourced community when the communication channel between the LLM developer and domain expert is constrained? We explored this question through a real-world case study, in which our data science team sought to partner with social workers at a safety net hospital to build an LLM application that summarizes patients' social needs. Whereas prior works focus on the challenge of prompt tuning, we found that the most critical challenge in this setting is the careful and precise specification of \what information to surface to providers so that the LLM application is accurate, comprehensive, and verifiable. Here we present a novel co-design framework for settings with limited access to domain experts, in which the summary generation task is first decomposed into individually-optimizable attributes and then each attribute is efficiently refined and validated through a multi-tier cascading approach.

We take a physics-based approach to studying how the internal hidden states of large language models change from token to token during inference. Across 20 open-source transformer models (135M-3B parameters), we find that a quantity combining the rate of change in hidden states and the model's next-token certainty, analogous to energy in physics, remains nearly constant. Random-weight models conserve this "energy" more tightly than pre-trained ones, while training shifts models into a faster, more decisive regime with greater variability. Using this "log-Lagrangian" view, we derive a control method called Jacobian steering, which perturbs hidden states in the minimal way needed to favor a target token. This approach maintained near-constant energy in two tested models and produced continuations rated higher in semantic quality than the models' natural outputs. Viewing transformers through this mechanics lens offers a principled basis for interpretability, anomaly detection, and low-risk steering. This could help make powerful models more predictable and aligned with human intent.

Alignment techniques for LLMs rely on optimizing preference-based objectives -- where these preferences are typically elicited as ordinal, binary choices between responses. Recent work has focused on improving label quality or mitigating particular biases, but we identify a more fundamental limitation: these methods collect the wrong kind of data. We prove an impossibility result: no algorithm relying solely on ordinal comparisons can systematically recover the most preferred model. Intuitively, ordinal data lacks the information needed to resolve tradeoffs -- e.g., fixing a factual error on one prompt versus improving style on another. We show that selecting the optimal model requires recovering preferences over \emph{models} (rather than just responses), which can only be identified given cardinal feedback about response quality. To address this, we collect and publicly release a dataset of 25,000 cardinal judgments using willingness-to-pay elicitations, a well-established tool from experimental economics. Empirically, we find that incorporating cardinal feedback into preference fine-tuning allows models to prioritize high-impact improvements and outperform ordinal-only methods on downstream benchmarks, such as Arena-Hard.

Despite their potential to enhance children's learning experiences, AI-enabled AR technologies are predominantly used in ways that position children as consumers rather than creators. We introduce Capybara, an AR-based and AI-powered visual programming environment that empowers children to create, customize, and program 3D characters overlaid onto the physical world. Capybara enables children to create virtual characters and accessories using text-to-3D generative AI models, and to animate these characters through auto-rigging and body tracking. In addition, our system employs vision-based AI models to recognize physical objects, allowing children to program interactive behaviors between virtual characters and their physical surroundings. We demonstrate the expressiveness of Capybara through a set of novel AR experiences. We conducted user studies with 20 children in the United States and Argentina. Our findings suggest that Capybara can empower children to harness AI in authoring personalized and engaging AR experiences that seamlessly bridge the virtual and physical worlds.

Accurately modeling user preferences is crucial for improving the performance of content-based recommender systems. Existing approaches often rely on simplistic user profiling methods, such as averaging or concatenating item embeddings, which fail to capture the nuanced nature of user preference dynamics, particularly the interactions between long-term and short-term preferences. In this work, we propose LLM-driven Temporal User Profiling (LLM-TUP), a novel method for user profiling that explicitly models short-term and long-term preferences by leveraging interaction timestamps and generating natural language representations of user histories using a large language model (LLM). These representations are encoded into high-dimensional embeddings using a pre-trained BERT model, and an attention mechanism is applied to dynamically fuse the short-term and long-term embeddings into a comprehensive user profile. Experimental results on real-world datasets demonstrate that LLM-TUP achieves substantial improvements over several baselines, underscoring the effectiveness of our temporally aware user-profiling approach and the use of semantically rich user profiles, generated by LLMs, for personalized content-based recommendation.

E-commerce search engines often rely solely on product titles as input for ranking models with latency constraints. However, this approach can result in suboptimal relevance predictions, as product titles often lack sufficient detail to capture query intent. While product descriptions provide richer information, their verbosity and length make them unsuitable for real-time ranking, particularly for computationally expensive architectures like cross-encoder ranking models. To address this challenge, we propose ReLSum, a novel reinforcement learning framework designed to generate concise, query-relevant summaries of product descriptions optimized for search relevance. ReLSum leverages relevance scores as rewards to align the objectives of summarization and ranking, effectively overcoming limitations of prior methods, such as misaligned learning targets. The framework employs a trainable large language model (LLM) to produce summaries, which are then used as input for a cross-encoder ranking model. Experimental results demonstrate significant improvements in offline metrics, including recall and NDCG, as well as online user engagement metrics. ReLSum provides a scalable and efficient solution for enhancing search relevance in large-scale e-commerce systems.

Collectible card games (CCGs) are a difficult genre for AI due to their partial observability, long-term decision-making, and evolving card sets. Due to this, current AI models perform vastly worse than human players at CCG tasks such as deckbuilding and gameplay. In this work, we introduce UrzaGPT, a domain-adapted large language model that recommends real-time drafting decisions in Magic: The Gathering. Starting from an open-weight LLM, we use Low-Rank Adaptation fine-tuning on a dataset of annotated draft logs. With this, we leverage the language modeling capabilities of LLM, and can quickly adapt to different expansions of the game. We benchmark UrzaGPT in comparison to zero-shot LLMs and the state-of-the-art domain-specific model. Untuned, small LLMs like Llama-3-8B are completely unable to draft, but the larger GPT-4o achieves a zero-shot performance of 43%. Using UrzaGPT to fine-tune smaller models, we achieve an accuracy of 66.2% using only 10,000 steps. Despite this not reaching the capability of domain-specific models, we show that solely using LLMs to draft is possible and conclude that using LLMs can enable performant, general, and update-friendly drafting AIs in the future.

Large Language Models (LLMs) are widely used for code generation. However, commercial models like ChatGPT require significant computing power, which leads to high energy use and carbon emissions. This has raised concerns about their environmental impact. In this study, we evaluate open-source Small Language Models (SLMs) trained explicitly for code generation and compare their performance and energy efficiency against large LLMs and efficient human-written Python code. The goal is to investigate whether SLMs can match the performance of LLMs on certain types of programming problems while producing more energy-efficient code. We evaluate 150 coding problems from LeetCode, evenly distributed across three difficulty levels: easy, medium, and hard. Our comparison includes three small open-source models, StableCode-3B, StarCoderBase-3B, and Qwen2.5-Coder-3B-Instruct, and two large commercial models, GPT-4.0 and DeepSeek-Reasoner. The generated code is evaluated using four key metrics: run-time, memory usage, energy consumption, and correctness. We use human-written solutions as a baseline to assess the quality and efficiency of the model-generated code. Results indicate that LLMs achieve the highest correctness across all difficulty levels, but SLMs are often more energy-efficient when their outputs are correct. In over 52% of the evaluated problems, SLMs consumed the same or less energy than LLMs.

While large language models (LLMs) challenge conventional methods of teaching and learning, they present an exciting opportunity to improve efficiency and scale high-quality instruction. One promising application is the generation of customized exams, tailored to specific course content. There has been significant recent excitement on automatically generating questions using artificial intelligence, but also comparatively little work evaluating the psychometric quality of these items in real-world educational settings. Filling this gap is an important step toward understanding generative AI's role in effective test design. In this study, we introduce and evaluate an iterative refinement strategy for question generation, repeatedly producing, assessing, and improving questions through cycles of LLM-generated critique and revision. We evaluate the quality of these AI-generated questions in a large-scale field study involving 91 classes -- covering computer science, mathematics, chemistry, and more -- in dozens of colleges across the United States, comprising nearly 1700 students. Our analysis, based on item response theory (IRT), suggests that for students in our sample the AI-generated questions performed comparably to expert-created questions designed for standardized exams. Our results illustrate the power of AI to make high-quality assessments more readily available, benefiting both teachers and students.