arXiv subjects

Hyoungsun Choi

Publications and source records attributed to Hyoungsun Choi.

5 recordsLinked to original sources

arXiv2025

How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control

Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts function as semantic conditions on how a fixed model interprets inputs, foregrounds information, and structures tasks. We formalize this account through three notions -- frame activation, salience control, and construal selection -- and study them in natural language inference, claim verification, and multi-hop question answering. Across these settings, prompts produce measurable changes in label judgments, evidence use, and answer-support organization, showing that prompt effects differ not only in magnitude but also in semantic direction. The paper therefore reframes prompting as the analysis of how instructions move model behavior, rather than only whether they improve performance.

cs.LG↗

arXiv2025

$\phi$-Table: A Statistical Explanation for Global SHAP

Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $\phi$-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response $f(X)$, reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the $\phi$-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior.

stat.ML↗

arXiv2025

CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regression

Conformal regression provides finite-sample marginal coverage, but it does not by itself determine how interval width should adapt across heterogeneous inputs. Existing locally adaptive methods mainly account for aleatoric noise, leaving uncertainty from weak training support less explicit. We propose Conformal Laplace-Aware Predictive Scaling (CLAPS), a split conformal regression method that uses heteroscedastic last-layer Laplace uncertainty as the local normalization scale. CLAPS combines learned input-dependent noise with last-layer epistemic uncertainty, while retaining validity through standard conformal calibration. We characterize this aleatoric--epistemic scale, derive its heteroscedastic last-layer precision, and show that it reduces to aleatoric local scaling as epistemic uncertainty contracts. Experiments show nominal-level coverage with competitive interval efficiency.

cs.LG↗

arXiv2025

CUBE: Contrastive Understanding by Balanced Experiments

Post-hoc explanation depends on how model queries are organized. We propose CUBE, a design-based framework that explains a trained predictive model through balanced low--high probes. Selected variables define factors, designed feature-level combinations define query conditions, and model predictions are summarized as factorial contrasts. CUBE reports main effects and pairwise interactions as controlled readings of average and conditional response changes over a declared design space. Experiments on synthetic and real tabular tasks show that CUBE recovers dominant learned effect structure, clarifies query-efficient identifiability, and supports screening--follow-up refinement.

cs.LG↗

arXiv2025

Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It

The success of federated learning (FL) ultimately depends on how strategic participants behave under partial observability, yet most formulations still treat FL as a static optimization problem. We instead view FL deployments as governed strategic systems and develop an analytical framework that separates welfare-improving behavior from metric gaming. Within this framework, we introduce indices that quantify manipulability, the price of gaming, and the price of cooperation, and we use them to study how rules, information disclosure, evaluation metrics, and aggregator-switching policies reshape incentives and cooperation patterns. We derive threshold conditions for deterring harmful gaming while preserving benign cooperation, and for triggering auto-switch rules when early-warning indicators become critical. Building on these results, we construct a design toolkit including a governance checklist and a simple audit-budget allocation algorithm with a provable performance guarantee. Simulations across diverse stylized environments and a federated learning case study consistently match the qualitative and quantitative patterns predicted by our framework. Taken together, our results provide design principles and operational guidelines for reducing metric gaming while sustaining stable, high-welfare cooperation in FL platforms.

cs.LG↗