Conferences & Journals

Agents

Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models

ACL 2026 (Main)

Jonggeun Lee*, Woojung Song*, Jongwook Han*, Haesung Pyun, Yohan Jo  Co-first

Proposes PA-Tool, a training-free method that renames tool schema components to align with small language models' pretraining familiarity, achieving up to 17% improvement on tool-use benchmarks without model retraining.

Value Alignment

Human Psychometric Questionnaires Mischaracterize LLM Psychology: Evidence from Generation Behavior

Under Review, 2026

Woojung Song*, Dongmin Choi*, Yoonah Park, Jongwook Han, Eun-Ju Lee, Yohan Jo  Co-first

Shows that psychological profiles of LLMs obtained via standard human questionnaires diverge substantially from profiles derived from their actual generation behavior, suggesting questionnaire-based assessments reflect desired rather than genuine traits.

Agents

Non-Collaborative User Simulators for Tool Agents

ICLR 2026

Jeonghoon Shim, Woojung Song, Cheyon Jin, Seungwon Kook, Yohan Jo

Introduces a user simulator that reproduces realistic non-collaborative behaviors (requesting unavailable services, digressing, expressing impatience), revealing that state-of-the-art tool agents suffer significant performance drops under such conditions.

Value Alignment

Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators

TACL, 2026

Sungjib Lim, Woojung Song, Eunju Lee, Yohan Jo

Uses LLMs as virtual respondents for validating psychometric survey items by modeling trait-response mediators, demonstrating cost-effective item validation across Big Five personality, Schwartz values, and VIA character strengths.

Value Alignment

Quantifying Data Contamination in Psychometric Evaluations of LLMs

EACL 2026 (Findings)

Jongwook Han*, Woojung Song*, Jonggeun Lee*, Yohan Jo  Co-first

Proposes a systematic framework to measure data contamination in psychometric LLM evaluations across item memorization, evaluation memorization, and target score matching, finding strong contamination in popular inventories like BFI and PVQ.

Value Alignment

Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items

ACL 2025 (Main)

Jongwook Han*, Dongmin Choi*, Woojung Song*, Eun-Ju Lee, Yohan Jo  Co-first

Proposes the Value Portrait framework for evaluating LLM values using items from real user-LLM interactions, finding across 44 LLMs that they emphasize Benevolence, Security, and Self-Direction while undervaluing Tradition, Power, and Achievement.

Applied ML

Interpretable Prediction of Private Brand Purchases by Pet Type in E-Commerce for Consumer Behavior Analysis Using Real-World Transaction Data

PeerJ CS, 2025

Jaehyuk Lee*, Woojung Song*, Jina Kim, Eunchan Kim  Co-first

Domestic Publications

Education

B. F. Sword: Blank Inference System with Optimized RAG and Knowledge Distillation

HCI Korea, 2025

Junseong Pyo, Hyejin Bae, Kitae Kwon, Jina Kim, Woojung Song, Yeonseong Shin

An LLM-based system for generating Korean college entrance exam English reading comprehension questions, combining abductive reasoning with RAG and knowledge distillation.

Applied ML

Enhancing the Security of AI Models through Parameter Encryption

KCC, 2025

Dongwook Kim, Woojung Song

Proposes a cryptographic access control technique that encrypts AI model parameters to prevent unauthorized access on lightweight on-device models, utilizing the ELU activation function to handle nonlinear operations under homomorphic encryption.