8 papers
AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
Chanhee Park, Jeongho Yoon, Sungbin Han +2
Agentic tasks require a large language model to interact with the world, navigating information and gathering evidence across multiple steps with restricted resources. Due to this…
Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models
Jeongho Yoon, Chanhee Park, Yongchan Chun +5
Cloud-based large language models (LLMs) require users to disclose plaintext data to service providers, creating privacy risks in sensitive domains. Existing privacy-preserving app…
Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning
Chanhee Park, Sungbin Han, Jeongho Yoon +2
Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deploym…
Response-Aware User Memory Selection for LLM Personalization
Jillian Fisher, Jennifer Neville, Chan Young Park
A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation…
Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
Yongchan Chun, Chanhee Park, Jeongho Yoon +2
Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncertainty estimation methods, such…
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
Jeongho Yoon, Chanhee Park, Yongchan Chun +2
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unautho…
KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
Dongjun Kim, Chanhee Park, Chanjun Park +1
The instruction-following capabilities of large language models (LLMs) are pivotal for numerous applications, from conversational agents to complex reasoning systems. However, curr…
MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
Chanhee Park, Hyeonseok Moon, Chanjun Park +1
Retrieval-Augmented Generation (RAG) has gained prominence as an effective method for enhancing the generative capabilities of Large Language Models (LLMs) through the incorporatio…