arXiv subjects

Kyunghyun Cho

Publications and source records attributed to Kyunghyun Cho.

At least 73 records · Page 4Linked to original sources

arXiv2025

Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks

Although large language models (LLMs) have shown promise in biomolecule optimization problems, they incur heavy computational costs and struggle to satisfy precise constraints. On the other hand, specialized solvers like LaMBO-2 offer efficiency and fine-grained control but require more domain expertise. Comparing these approaches is challenging due to expensive laboratory validation and inadequate synthetic benchmarks. We address this by introducing Ehrlich functions, a synthetic test suite that captures the geometric structure of biophysical sequence optimization problems. With prompting alone, off-the-shelf LLMs struggle to optimize Ehrlich functions. In response, we propose LLOME (Language Model Optimization with Margin Expectation), a bilevel optimization routine for online black-box optimization. When combined with a novel preference learning loss, we find LLOME can not only learn to solve some Ehrlich functions, but can even perform as well as or better than LaMBO-2 on moderately difficult Ehrlich variants. However, LLMs also exhibit some likelihood-reward miscalibration and struggle without explicit rewards. Our results indicate LLMs can occasionally provide significant benefits, but specialized solvers are still competitive and incur less overhead.

cs.LG↗

arXiv2025

Deep Autoregressive Models as Causal Inference Engines

Existing causal inference (CI) models are often restricted to data with low-dimensional confounders and singleton actions. We propose an autoregressive (AR) CI framework capable of handling complex confounders and sequential actions commonly found in modern applications. Our approach accomplishes this using {\em sequencification}, which transforms data from an underlying causal diagram into a sequence of tokens. Sequencification not only accommodates training with data generated from a large class of DAGs, but also extends existing CI capabilities to estimate multiple causal quantities using a {\em single} model. We can directly compute probabilities from interventional distributions, simplifying inference and improving outcome prediction accuracy. We demonstrate that an AR model adapted for CI is efficient and effective in various complex applications such as navigating mazes, playing chess endgames, and evaluating the impact of certain keywords on paper acceptance rates, where we consider causal queries beyond standard reinforcement learning-type questions.

cs.LG↗

arXiv2025

Foundation Models for Clinical Records at Health System Scale

Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Our model is evaluated via zero-shot prediction for forecasting dementia and knee osteoarthritis incidence within 2 and 5 years, and the model performance rivals a fully fine-tuned masked pretrained Transformer baseline, demonstrating that our approach captures complex clinical dependencies without requiring costly task-specific fine-tuning.

cs.LG↗

arXiv2025

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback. While reinforcement learning (RL) has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO (State-Thinking-Actions-Reward Policy Optimization), a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents. Our study on four stylized environments reveals three core findings. First, our agent RL training shows a recurring mode of Echo Trap where reward variance cliffs and gradient spikes; we address this with StarPO-S, a stabilized variant with trajectory filtering, critic incorporation, and gradient stabilization. Second, we find the shaping of RL rollouts would benefit from diverse initial states, medium interaction granularity and more frequent sampling. Third, we show that without fine-grained, reasoning-aware reward signals, agent reasoning hardly emerge through multi-turn RL and they may show shallow strategies or hallucinated thoughts. Code and environments are available at https://github.com/RAGEN-AI/RAGEN.

cs.LG↗

arXiv2025

Machine Learning: a Lecture Note

This lecture note is intended to prepare early-year master's and PhD students in data science or a related discipline with foundational ideas in machine learning. It starts with basic ideas in modern machine learning with classification as a main target task. These basic ideas include loss formulation, backpropagation, stochastic gradient descent, generalization, model selection as well as fundamental blocks of artificial neural networks. Based on these basic ideas, the lecture note explores in depth the probablistic approach to unsupervised learning, covering directed latent variable models, product of experts, generative adversarial networks and autoregressive models. Finally, the note ends by covering a diverse set of further topics, such as reinforcement learning, ensemble methods and meta-learning. After reading this lecture note, a student should be ready to embark on studying and researching more advanced topics in machine learning and more broadly artificial intelligence.

cs.LG↗

arXiv2025

Aioli: A Unified Optimization Framework for Language Model Data Mixing

Language model performance depends on identifying the optimal mixture of data groups to train on (e.g., law, code, math). Prior work has proposed a diverse set of methods to efficiently learn mixture proportions, ranging from fitting regression models over training runs to dynamically updating proportions throughout training. Surprisingly, we find that no existing method consistently outperforms a simple stratified sampling baseline in terms of average test perplexity. To understand this inconsistency, we unify existing methods into a standard framework, showing they are equivalent to solving a common optimization problem: minimize average loss subject to a method-specific mixing law -- an implicit assumption on the relationship between loss and mixture proportions. This framework suggests that measuring the fidelity of a method's mixing law can offer insights into its performance. Empirically, we find that existing methods set their mixing law parameters inaccurately, resulting in the inconsistent mixing performance we observe. Using this insight, we derive a new online method named Aioli, which directly estimates the mixing law parameters throughout training and uses them to dynamically adjust proportions. Aioli outperforms stratified sampling on 6 out of 6 datasets by an average of 0.27 test perplexity points, whereas existing methods fail to consistently beat stratified sampling, doing up to 6.9 points worse. Moreover, in a practical setting where proportions are learned on shorter runs due to computational constraints, Aioli can dynamically adjust these proportions over the full training run, consistently improving performance over existing methods by up to 12.012 test perplexity points.

cs.LG↗

arXiv2025

Self-Rewarding Language Models

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by human performance level, and secondly these separate frozen reward models cannot then learn to improve during LLM training. In this work, we study Self-Rewarding Language Models, where the language model itself is used via LLM-as-a-Judge prompting to provide its own rewards during training. We show that during Iterative DPO training that not only does instruction following ability improve, but also the ability to provide high-quality rewards to itself. Fine-tuning Llama 2 70B on three iterations of our approach yields a model that outperforms many existing systems on the AlpacaEval 2.0 leaderboard, including Claude 2, Gemini Pro, and GPT-4 0613. While there is much left still to explore, this work opens the door to the possibility of models that can continually improve in both axes.

cs.CL↗

arXiv2025

A Progressive Risk Formulation for Enhanced Deep Learning based Total Knee Replacement Prediction in Knee Osteoarthritis

We developed deep learning models for predicting Total Knee Replacement (TKR) need within various time horizons in knee osteoarthritis patients, with a novel capability: the models can perform TKR prediction using a single scan, and furthermore when a previous scan is available, they leverage a progressive risk formulation to improve their predictions. Unlike conventional approaches that treat each scan of a patient independently, our method incorporates a constraint based on disease's progressive nature, ensuring that predicted TKR risk either increases or remains stable over time when multiple scans of a knee are available. This was achieved by enforcing a progressive risk formulation constraint during training with patients who have more than one available scan in the studies. Knee radiographs and MRIs from the Osteoarthritis Initiative (OAI) and Multicenter Osteoarthritis Study (MOST) were used in this work and deep learning models were trained to predict TKR within 1, 2, and 4-year time periods. The proposed approach, utilizing a dual-model risk constraint architecture, demonstrated superior performance compared to baseline - conventional models trained with standard binary cross entropy loss. It achieved an AUROC of 0.87 and AUPRC of 0.47 for 1-year TKR prediction on the OAI radiograph test set, considerably improving over the baseline AUROC of 0.79 and AUPRC of 0.34. For the MOST radiograph test set, the proposed approach achieved an AUROC of 0.77 and AUPRC of 0.25 for 1-year predictions, outperforming the baseline AUROC of 0.71 and AUPRC of 0.19. Similar trends were observed in the MRI testsets

eess.IV↗

arXiv2025

How To Think About End-To-End Encryption and AI: Training, Processing, Disclosure, and Consent

End-to-end encryption (E2EE) has become the gold standard for securing communications, bringing strong confidentiality and privacy guarantees to billions of users worldwide. However, the current push towards widespread integration of artificial intelligence (AI) models, including in E2EE systems, raises some serious security concerns. This work performs a critical examination of the (in)compatibility of AI models and E2EE applications. We explore this on two fronts: (1) the integration of AI "assistants" within E2EE applications, and (2) the use of E2EE data for training AI models. We analyze the potential security implications of each, and identify conflicts with the security guarantees of E2EE. Then, we analyze legal implications of integrating AI models in E2EE applications, given how AI integration can undermine the confidentiality that E2EE promises. Finally, we offer a list of detailed recommendations based on our technical and legal analyses, including: technical design choices that must be prioritized to uphold E2EE security; how service providers must accurately represent E2EE security; and best practices for the default behavior of AI features and for requesting user consent. We hope this paper catalyzes an informed conversation on the tensions that arise between the brisk deployment of AI and the security offered by E2EE, and guides the responsible development of new AI features.

cs.CR↗

arXiv2025

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs

Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model. However, certain insights into model behavior may only be accessible by observing the trajectory of the training process. We present a case study of syntax acquisition in masked language models (MLMs) that demonstrates how analyzing the evolution of interpretable artifacts throughout training deepens our understanding of emergent behavior. In particular, we study Syntactic Attention Structure (SAS), a naturally emerging property of MLMs wherein specific Transformer heads tend to focus on specific syntactic relations. We identify a brief window in pretraining when models abruptly acquire SAS, concurrent with a steep drop in loss. This breakthrough precipitates the subsequent acquisition of linguistic capabilities. We then examine the causal role of SAS by manipulating SAS during training, and demonstrate that SAS is necessary for the development of grammatical capabilities. We further find that SAS competes with other beneficial traits during training, and that briefly suppressing SAS improves model quality. These findings offer an interpretation of a real-world example of both simplicity bias and breakthrough training dynamics.

cs.CL↗

arXiv2025

Semiparametric conformal prediction

Many risk-sensitive applications require well-calibrated prediction sets over multiple, potentially correlated target variables, for which the prediction algorithm may report correlated errors. In this work, we aim to construct the conformal prediction set accounting for the joint correlation structure of the vector-valued non-conformity scores. Drawing from the rich literature on multivariate quantiles and semiparametric statistics, we propose an algorithm to estimate the $1-α$ quantile of the scores, where $α$ is the user-specified miscoverage rate. In particular, we flexibly estimate the joint cumulative distribution function (CDF) of the scores using nonparametric vine copulas and improve the asymptotic efficiency of the quantile estimate using its influence function. The vine decomposition allows our method to scale well to a large number of targets. As well as guaranteeing asymptotically exact coverage, our method yields desired coverage and competitive efficiency on a range of real-world regression problems, including those with missing-at-random labels in the calibration set.

cs.LG↗

arXiv2025

Black Box Causal Inference: Effect Estimation via Meta Prediction

Causal inference and the estimation of causal effects plays a central role in decision-making across many areas, including healthcare and economics. Estimating causal effects typically requires an estimator that is tailored to each problem of interest. But developing estimators can take significant effort for even a single causal inference setting. For example, algorithms for regression-based estimators, propensity score methods, and doubly robust methods were designed across several decades to handle causal estimation with observed confounders. Similarly, several estimators have been developed to exploit instrumental variables (IVs), including two-stage least-squares (TSLS), control functions, and the method-of-moments. In this work, we instead frame causal inference as a dataset-level prediction problem, offloading algorithm design to the learning process. The approach we introduce, called black box causal inference (BBCI), builds estimators in a black-box manner by learning to predict causal effects from sampled dataset-effect pairs. We demonstrate accurate estimation of average treatment effects (ATEs) and conditional average treatment effects (CATEs) with BBCI across several causal inference problems with known identification, including problems with less developed estimators.

cs.LG↗

arXiv2025

An Overview of Large Language Models for Statisticians

Large Language Models (LLMs) have emerged as transformative tools in artificial intelligence (AI), exhibiting remarkable capabilities across diverse tasks such as text generation, reasoning, and decision-making. While their success has primarily been driven by advances in computational power and deep learning architectures, emerging problems -- in areas such as uncertainty quantification, decision-making, causal inference, and distribution shift -- require a deeper engagement with the field of statistics. This paper explores potential areas where statisticians can make important contributions to the development of LLMs, particularly those that aim to engender trustworthiness and transparency for human users. Thus, we focus on issues such as uncertainty quantification, interpretability, fairness, privacy, watermarking and model adaptation. We also consider possible roles for LLMs in statistical analysis. By bridging AI and statistics, we aim to foster a deeper collaboration that advances both the theoretical foundations and practical applications of LLMs, ultimately shaping their role in addressing complex societal challenges.

stat.ML↗

arXiv2025

Supervised Contrastive Block Disentanglement

Real-world datasets often combine data collected under different experimental conditions. This yields larger datasets, but also introduces spurious correlations that make it difficult to model the phenomena of interest. We address this by learning two embeddings to independently represent the phenomena of interest and the spurious correlations. The embedding representing the phenomena of interest is correlated with the target variable $y$, and is invariant to the environment variable $e$. In contrast, the embedding representing the spurious correlations is correlated with $e$. The invariance to $e$ is difficult to achieve on real-world datasets. Our primary contribution is an algorithm called Supervised Contrastive Block Disentanglement (SCBD) that effectively enforces this invariance. It is based purely on Supervised Contrastive Learning, and applies to real-world data better than existing approaches. We empirically validate SCBD on two challenging problems. The first problem is domain generalization, where we achieve strong performance on a synthetic dataset, as well as on Camelyon17-WILDS. We introduce a single hyperparameter $α$ to control the degree of invariance to $e$. When we increase $α$ to strengthen the degree of invariance, out-of-distribution performance improves at the expense of in-distribution performance. The second problem is batch correction, in which we apply SCBD to preserve biological signal and remove inter-well batch effects when modeling single-cell perturbations from 26 million Optical Pooled Screening images.

cs.LG↗

arXiv2025

The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models

Decoder-only language models have the ability to dynamically switch between various computational tasks based on input prompts. Despite many successful applications of prompting, there is very limited understanding of the internal mechanism behind such flexibility. In this work, we investigate how different prompting methods affect the geometry of representations in these models. Employing a framework grounded in statistical physics, we reveal that various prompting techniques, while achieving similar performance, operate through distinct representational mechanisms for task adaptation. Our analysis highlights the critical role of input distribution samples and label semantics in few-shot in-context learning. We also demonstrate evidence of synergistic and interfering interactions between different tasks on the representational level. Our work contributes to the theoretical understanding of large language models and lays the groundwork for developing more effective, representation-aware prompting strategies.

cs.CL↗

arXiv2025

HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja

While Korean historical documents are invaluable cultural heritage, understanding those documents requires in-depth Hanja expertise. Hanja is an ancient language used in Korea before the 20th century, whose characters were borrowed from old Chinese but had evolved in Korea for centuries. Modern Koreans and Chinese cannot understand Korean historical documents without substantial additional help, and while previous efforts have produced some Korean and English translations, this requires in-depth expertise, and so most of the documents are not translated into any modern language. To address this gap, we present HERITAGE, the first open-source Hanja NLP toolkit to assist in understanding and translating the unexplored Korean historical documents written in Hanja. HERITAGE is a web-based platform providing model predictions of three critical tasks in historical document understanding via Hanja language models: punctuation restoration, named entity recognition, and machine translation (MT). HERITAGE also provides an interactive glossary, which provides the character-level reading of the Hanja characters in modern Korean, as well as character-level English definition. HERITAGE serves two purposes. First, anyone interested in these documents can get a general understanding from the model predictions and the interactive glossary, especially MT outputs in Korean and English. Second, since the model outputs are not perfect, Hanja experts can revise them to produce better annotations and translations. This would boost the translation efficiency and potentially lead to most of the historical documents being translated into modern languages, lowering the barrier on unexplored Korean historical documents.

cs.CL↗

arXiv2024

xVal: A Continuous Numerical Tokenization for Scientific Language Models

Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets. Rendering datasets as text, however, could help aggregate diverse and multi-modal scientific data into a single training corpus, thereby potentially facilitating the development of foundation models for science. In this work, we introduce xVal, a strategy for continuously tokenizing numbers within language models that results in a more appropriate inductive bias for scientific applications. By training specially-modified language models from scratch on a variety of scientific datasets formatted as text, we find that xVal generally outperforms other common numerical tokenization strategies on metrics including out-of-distribution generalization and computational efficiency.

stat.ML↗

arXiv2024

Concept Bottleneck Language Models For protein design

We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our architecture offers three key benefits: i) Control: We can intervene on concept values to precisely control the properties of generated proteins, achieving a 3 times larger change in desired concept values compared to baselines. ii) Interpretability: A linear mapping between concept values and predicted tokens allows transparent analysis of the model's decision-making process. iii) Debugging: This transparency facilitates easy debugging of trained models. Our models achieve pre-training perplexity and downstream task performance comparable to traditional masked protein language models, demonstrating that interpretability does not compromise performance. While adaptable to any language model, we focus on masked protein language models due to their importance in drug discovery and the ability to validate our model's capabilities through real-world experiments and expert knowledge. We scale our CB-pLM from 24 million to 3 billion parameters, making them the largest Concept Bottleneck Models trained and the first capable of generative language modeling.

cs.LG↗