35 citations · 81 across the 27 of their papers we have counts for
28 papers
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1
Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safety policies (safety-based re…
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
Hwiyeong Lee, Ingyu Bang, Uiji Hwang +2
While sparse autoencoders provide features more interpretable than individual neurons, reliably characterizing them remains challenging. We propose Query Lens, which extends Logit…
UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge
Youna Kim, Hyuhng Joon Kim, Minjoon Choi +4
Language models often benefit from external knowledge beyond parametric knowledge. While this combination enhances performance, achieving reliable knowledge utilization remains cha…
When to Speak, When to Abstain: Contrastive Decoding with Abstention
Hyuhng Joon Kim, Youna Kim, Sang-goo Lee +1
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While…
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
Youna Kim, Hyuhng Joon Kim, Cheonbok Park +6
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the…
Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection
Choonghyun Park, Hyuhng Joon Kim, Junyeob Kim +6
AI Generated Text (AIGT) detectors are developed with texts from humans and LLMs of common tasks. Despite the diversity of plausible prompt choices, these datasets are generally co…