8 papers · 1 filter
PARTREP: Learning What to Repeat for Decoder-only LLMs
Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim +1
While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in cont…
Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval
Jihyung lee, Hyounghun Kim, Gary Lee
Large language models (LLMs) have shown strong performance in the legal domain, demonstrating notable potential in Legal Question Answering (LQA). However, unlike general QA, LQA r…
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
Seonjeong Hwang, Jun Seo, Hyounghun Kim +1
Recent studies in difficulty-controlled reading comprehension item generation have leveraged large language models (LLMs) to produce items by adjusting difficulty-related features.…
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
Jun Seo, Sangwon Ryu, Heejin Do +2
Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with…
Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
Wonjun Lee, Hyounghun Kim, Gary Geunbae Lee
Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leadin…
Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
Deokhyung Kang, Seonjeong Hwang, Daehui Kim +2
Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap, performing better in high-resource lang…
Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?
Seonjeong Hwang, Hyounghun Kim, Gary Geunbae Lee
Estimating the cognitive complexity of reading comprehension (RC) items is crucial for assessing item difficulty before it is administered to learners. Unlike syntactic and semanti…
KoBLEX: Open Legal Question Answering with Multi-hop Reasoning
Jihyung Lee, Daehui Kim, Seonjeong Hwang +2
Large Language Models (LLM) have achieved remarkable performances in general domains and are now extending into the expert domain of law. Several benchmarks have been proposed to e…