53 citations · 54 across the 9 of their papers we have counts for
9 papers
RLDX-1 Technical Report
Dongyoung Kim, Huiwon Jang, Myungkyu Koo +65
While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene underst…
How Much Heavy Lifting Can an Agent Harness Do?: Measuring the LLM's Residual Role in a Planning Agent
Sungwoo Jung, Seonil Son
Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as mu…
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
Zipeng Ling, Shuliang Liu, Seonil Son +4
Large language models (LLMs) have become increasingly used for various tasks, often coupled with Chain-of-Thought (CoT) prompting to boost accuracy. Recent work has shown that high…
LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
Zipeng Ling, Shuliang Liu, Yuehao Tang +8
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misapplied: in real-world applicatio…
Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons
Seonil Son, Ju-Min Oh, Heegon Jin +3
As Large Language Models (LLMs) expand across domains, LLM judges have become essential for systems evaluation. Current benchmarks typically compare system outputs against baseline…
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
Heegon Jin, Seonil Son, Jemin Park +3
The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring kn…
HaRiM: Evaluating Summary Quality with Hallucination Risk
Seonil Son, Junsoo Park, Jeong-in Hwang +3
One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the…
Learning to Write with Coherence From Negative Examples
Seonil Son, Jaeseo Lim, Youwon Jang +2
Coherence is one of the critical factors that determine the quality of writing. We propose writing relevance (WR) training method for neural encoder-decoder natural language genera…
GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation
Taehyeong Kim, Min-Oh Heo, Seonil Son +2
The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images. The…