1 citations · 1 across the 4 of their papers we have counts for
5 papers · 1 filter
Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines
Yoon Jeonghun, Kim Dongchan
When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Diagnostic Paradox empirically:…
CUE-M: Contextual Understanding and Enhanced Search with Multimodal Large Language Model
Dongyoung Go, Taesun Whang, Chanhee Lee +6
The integration of Retrieval-Augmented Generation (RAG) with Multimodal Large Language Models (MLLMs) has revolutionized information retrieval and expanded the practical applicatio…
Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
JIhwan Lee, Dongchan Kim, Ruhi Sarikaya +1
Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new mo…
Efficient Large-Scale Domain Classification with Personalized Attention
Young-Bum Kim, Dongchan Kim, Anjishnu Kumar +1
In this paper, we explore the task of mapping spoken language utterances to one of thousands of natural language understanding domains in intelligent personal digital assistants (I…
A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding
Young-Bum Kim, Dongchan Kim, Joo-Kyung Kim +1
Intelligent personal digital assistants (IPDAs), a popular real-life application with spoken language understanding capabilities, can cover potentially thousands of overlapping dom…