Hailey Joren

Salva Rühling Cachay, Bo Zhao, Hailey Joren et al.

While diffusion models can successfully generate data and make predictions, they are predominantly designed for static images. We propose an approach for efficiently training diffusion models for probabilistic spatiotemporal forecasting, where generating stable and accurate rollout forecasts remains challenging, Our method, DYffusion, leverages the temporal dynamics in the data, directly coupling it with the diffusion steps in the model. We train a stochastic, time-conditioned interpolator and a forecaster network that mimic the forward and reverse processes of standard diffusion models, respectively. DYffusion naturally facilitates multi-step and long-range forecasting, allowing for highly flexible, continuous-time sampling trajectories and the ability to trade-off performance with accelerated sampling at inference time. In addition, the dynamics-informed diffusion process in DYffusion imposes a strong inductive bias and significantly improves computational efficiency compared to traditional Gaussian noise-based diffusion models. Our approach performs competitively on probabilistic forecasting of complex dynamics in sea surface temperatures, Navier-Stokes flows, and spring mesh systems.

Hailey Joren, Chirag Nagpal, Katherine Heller et al.

Machine learning models are often personalized with information that is protected, sensitive, self-reported, or costly to acquire. These models use information about people but do not facilitate nor inform their consent. Individuals cannot opt out of reporting personal information to a model, nor tell if they benefit from personalization in the first place. We introduce a family of classification models, called participatory systems, that let individuals opt into personalization at prediction time. We present a model-agnostic algorithm to learn participatory systems for personalization with categorical group attributes. We conduct a comprehensive empirical study of participatory systems in clinical prediction tasks, benchmarking them with common approaches for personalization and imputation. Our results demonstrate that participatory systems can facilitate and inform consent while improving performance and data use across all groups who report personal data.

Elizabeth Donoway, Hailey Joren, Fabien Roger et al.

Understanding whether fine-tuning elicits latent capabilities or teaches new ones is a fundamental question for language model evaluation and safety. We develop a formal information-theoretic framework for quantifying how much predictive structure fine-tuning extracts from the train dataset and writes into a model's parameters. Our central quantity, Excess Description Length (EDL), is defined via prequential coding and measures the gap between the bits required to encode training labels sequentially using an evolving model (trained online) and the residual encoding cost under the final trained model. We establish that EDL is non-negative in expectation, converges to surplus description length in the infinite-data limit, and provides bounds on expected generalization gain. Through a series of toy models, we clarify common confusions about information in learning: why random labels yield EDL near zero, how a single example can eliminate many bits of uncertainty about the underlying rule(s) that describe the data distribution, why structure learned on rare inputs contributes proportionally little to expected generalization, and how format learning creates early transients distinct from capability acquisition. This framework provides rigorous foundations for the empirical observation that capability elicitation and teaching exhibit qualitatively distinct scaling signatures.

Hailey Joren, Jianyi Zhang, Chun-Sung Ferng et al.

Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a method to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that larger models with higher baseline performance (Gemini 1.5 Pro, GPT 4o, Claude 3.5) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, smaller models with lower baseline performance (Mistral 3, Gemma 2) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10\% for Gemini, GPT, and Gemma. Key findings and the prompts used in our autorater analysis are available on our github.

Hailey Joren, Charles Marx, Berk Ustun

We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the presence of intermediate concepts. Given this architecture, a safeguard ensures that a model meets a minimal level of accuracy by abstaining from uncertain predictions. In contrast to a standard selective classifier, a safeguard provides an avenue to improve coverage by allowing a human to confirm the presence of uncertain concepts on instances on which it abstains. We develop methods to build safeguards that maximize coverage without compromising safety, namely techniques to propagate the uncertainty in concept predictions and to flag salient concepts for human review. We benchmark our approach on a collection of real-world and synthetic datasets, showing that it can improve performance and coverage in deep learning tasks.

Hailey Joren, Otkrist Gupta, Dan Raviv

Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible. Nearly all approaches in this domain rely on a procedural approach, using carefully generated features and a hand-tuned scoring system, rather than a data-driven and generalizable approach. We frame this issue as a graph comparison problem using the character bounding boxes, and propose a model that leverages graph features using OCR (Optical Character Recognition). Our model relies on a data-driven approach to detect alterations by training a random forest classifier on the graph-based OCR features. We evaluate our algorithm's forgery detection performance on dataset constructed from real business documents with slight forgery imperfections. Our proposed model dramatically outperforms the most closely-related document manipulation detection model on this task.

Hailey Joren, Otkrist Gupta, Dan Raviv

Examining the authenticity of images has become increasingly important as manipulation tools become more accessible and advanced. Recent work has shown that while CNN-based image manipulation detectors can successfully identify manipulations, they are also vulnerable to adversarial attacks, ranging from simple double JPEG compression to advanced pixel-based perturbation. In this paper we explore another method of highly plausible attack: printing and scanning. We demonstrate the vulnerability of two state-of-the-art models to this type of attack. We also propose a new machine learning model that performs comparably to these state-of-the-art models when trained and validated on printed and scanned images. Of the three models, our proposed model outperforms the others when trained and validated on images from a single printer. To facilitate this exploration, we create a dataset of over 6,000 printed and scanned image blocks. Further analysis suggests that variation between images produced from different printers is significant, large enough that good validation accuracy on images from one printer does not imply similar validation accuracy on identical images from a different printer.

Hailey Joren, David Alvarez-Melis

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods hide but fail to truly remove the biases, which can still be observed in word nearest-neighbor statistics. In this work we propose a probabilistic view of word embedding bias. We leverage this framework to present a novel method for mitigating bias which relies on probabilistic observations to yield a more robust bias mitigation algorithm. We demonstrate that this method effectively reduces bias according to three separate measures of bias while maintaining embedding quality across various popular benchmark semantic tasks