8 papers · 1 filter
Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning
Sangmook Lee, Minbeom Kim, Jeonghye Kim +3
Diversity in LLM mathematical reasoning is critical for exploration, but common diversity metrics mostly capture surface-level variation rather than differences in how a problem is…
Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR
Dohyung Kim, Minbeom Kim, Jeonghye Kim +3
Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation diversity. Recent works address this issu…
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Jeonghye Kim, Xufang Luo, Minbeom Kim +5
Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we…
ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
Jeonghye Kim, Sojeong Rhee, Minbeom Kim +4
Recent advances in LLM agents have largely built on reasoning backbones like ReAct, which interleave thought and action in complex environments. However, ReAct often produces ungro…
Guaranteed Generation from Large Language Models
Minbeom Kim, Thibaut Thonet, Jos Rozen +3
As large language models (LLMs) are increasingly used across various applications, there is a growing need to control text generation to satisfy specific constraints or requirement…
Drift: Decoding-time Personalized Alignments with Implicit User Preferences
Minbeom Kim, Kang-il Lee, Seongho Joo +3
Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decodin…