12 papers
Answer First, Reason Later: Commitment Order in Diffusion LLMs
Jewon Yeom, Jaewon Sok, Seonghyeon Park +3
Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding. We show that on reasoning tasks…
Stable On-Policy Distillation through Adaptive Target Reformulation
Ijun Jang, Jewon Yeom, Juan Yeo +2
Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often…
Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA
Kyubyung Chae, Jewon Yeom, Jeongjae Park +5
Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory domains, relevant evidence is di…
What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction
Jewon Yeom, Hanseul Kim, Jeongjae Park +3
Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their la…
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
Jewon Yeom, Jaewon Sok, Heejun Kim +3
Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and…
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
Heejun Kim, Seungpil Lee, Jewon Yeom +5
Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned content or from the act of inje…