1 citations · 1 across the 3 of their papers we have counts for
6 papers
Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection
Hojin Kim, Jaehyung Kim
Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher confidence reflects higher reaso…
Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
Minseo Kwak, Jaehyung Kim
The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significant privacy and copyright concerns, making pretraining data detection a critical challenge…
EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
Hamin Koo, Jaehyung Kim
Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performa…
Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
Hamin Koo, Minseon Kim, Jaehyung Kim
Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass saf…
SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation
Seoyeon Kim, Jaehyung Kim
Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time. However, real-world interacti…
PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases
Yubeen Bae, Minchan Kim, Jaejin Lee +4
Large language models (LLMs) are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-of…