7 papers
Revisiting Complete Reasoning Traces for Post-Training
Jaehui Hwang, Sangdoo Yun, Byeongho Heo +1
Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability. Such trajectories tend to be long due to complex,…
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Seogyeong Jeong, Jaehui Hwang, Dongyoon Han +3
Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are expl…
On-Policy Delta Distillation for Multilingual Math Reasoning
Byeongho Heo, Jaehui Hwang, Sangdoo Yun +1
On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexp…
On-Policy Delta Distillation
Byeongho Heo, Jaehui Hwang, Sangdoo Yun +1
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervisio…
MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
Geonmo Gu, Byeongho Heo, Jaemyung Yu +7
Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-targ…
Oops, Wait: Discourse Tokens Matter in Reasoning Model
Jaehui Hwang, Byeongho Heo, Sangdoo Yun +1
Recent studies suggest that even data-efficient training with (1K) reasoning trajectories can induce non-trivial reasoning capabilities in large language models through pos…
What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
Heejin Do, Jaehui Hwang, Dongyoon Han +2
Evaluating large language models (LLMs) on final-answer correctness is the dominant paradigm. This approach, however, provides a coarse signal for model improvement and overlooks t…