Papers by Jongwook Han

4 papers
Quantifying Data Contamination in Psychometric Evaluations of LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Existing studies have raised concerns about data contamination from psychometric inventories . however, there is no systematic attempt to quantify the extent of data contamination .
Approach: They propose a framework to measure data contamination in psychometric evaluations of Large Language Models by item memorization, evaluation memorisation and target score matching.
Outcome: The proposed framework evaluates item memorization, evaluation memorisation, and target score matching in 21 models from major families and four widely used psychometric inventories.
Don’t Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models (2026.acl-long)

Copied to clipboard

Challenge: Small language models struggle with tool-use tasks, particularly in selecting appropriate tools and identifying correct parameters.
Approach: They propose a training-free method that leverages peakedness to align schemas with pretraining knowledge to rename tool components.
Outcome: Experiments on MetaTool and RoTBench show that PA-Tool significantly improves tool-use accuracy without retraining.
Value Portrait: Assessing Language Models’ Values through Psychometrically and Ecologically Valid Items (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks rely on human annotations that are vulnerable to value-related biases.
Approach: They propose a value portrait benchmark that uses items that capture real-life user-LLM interactions and a rated item based on its similarity to their own thoughts to determine reliability.
Outcome: The proposed framework improves the relevance of assessment results to real-world LLM usage by allowing human subjects to rate items with similarity to their own thoughts and derived correlations between these ratings and the subjects’ actual value scores.
PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness Ratings (2025.acl-long)

Copied to clipboard

Challenge: Visual persuasion uses visual elements to influence cognition and behaviors . lack of comprehensive data sets connect persuasiveness of images with personal information .
Approach: They propose to use a dataset to connect persuasiveness with personal information . they find psychological characteristics enhance the generation and evaluation of persuasive images .
Outcome: The proposed dataset provides persuasiveness scores of images evaluated by human annotators along with demographic and psychological characteristics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations