5 papers
When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text
DongHyun Ryu, Jaehyeok Lee, YeongJun Hwang +1
Large language models are increasingly used as judges to measure social bias in text, yet the passages they judge are often noisy, containing typos, informal spelling, and broken p…
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
Jaehyeok Lee, Xiaoyuan Yi, Jing Yao +4
As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Co…
Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages
Tarek Naous, Anagha Savit, Carlos Rafael Catalan +17
As Large Language Models (LLMs) develop stronger multilingual capabilities, their sensitivity to culturally diverse entities becomes increasingly important. Prior work by Naous et…
Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
Sooyung Choi, Jaehyeok Lee, Xiaoyuan Yi +3
The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these…
Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
Jaehyeok Lee, Keisuke Sakaguchi, JinYeong Bak
Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rat…