2 citations · 3 across the 16 of their papers we have counts for
17 papers
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…
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6
As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete de…
ReflectCAP: Detailed Image Captioning with Reflective Memory
Kyungmin Min, Minbeom Kim, Kang-il Lee +2
Detailed image captioning demands both factual grounding and fine-grained coverage, yet existing methods have struggled to achieve them simultaneously. We address this tension with…
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…
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
Jeonghye Kim, Xufang Luo, Minbeom Kim +3
LLMs often exhibit Aha moments such as self-correction after tokens like "Wait," yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergen…
CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
Minbeom Kim, Mihir Parmar, Phillip Wallis +5
AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted co…
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…
Program Synthesis via Test-Time Transduction
Kang-il Lee, Jahyun Koo, Seunghyun Yoon +4
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to progr…
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…
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…
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
Kyungmin Min, Minbeom Kim, Kang-il Lee +2
Large Vision-Language Models (LVLMs) demonstrate impressive capabilities in generating detailed and coherent responses from visual inputs. However, they are prone to generate hallu…
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…
A Character-Centric Creative Story Generation via Imagination
Kyeongman Park, Minbeom Kim, Kyomin Jung
Creative story generation has long been a goal of NLP research. While existing methodologies have aimed to generate long and coherent stories, they fall significantly short of huma…
VLind-Bench: Measuring Language Priors in Large Vision-Language Models
Kang-il Lee, Minbeom Kim, Seunghyun Yoon +4
Large Vision-Language Models (LVLMs) have demonstrated outstanding performance across various multimodal tasks. However, they suffer from a problem known as language prior, where r…
AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
Minbeom Kim, Hwanhee Lee, Joonsuk Park +2
As the integration of large language models into daily life is on the rise, there is a clear gap in benchmarks for advising on subjective and personal dilemmas. To address this, we…
LifeTox: Unveiling Implicit Toxicity in Life Advice
Minbeom Kim, Jahyun Koo, Hwanhee Lee +3
As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a datase…
Critic-Guided Decoding for Controlled Text Generation
Minbeom Kim, Hwanhee Lee, Kang Min Yoo +3
Steering language generation towards objectives or away from undesired content has been a long-standing goal in utilizing language models (LM). Recent work has demonstrated reinfor…