2 citations · 3 across the 11 of their papers we have counts for
11 papers
Language Models Can Control Their Own Attention
Namgyu Ho, Huzama Ahmad, Woosung Koh +3
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If the user asks about a previou…
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim, Namgyu Ho, Sangmin Hwang +7
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt th…
PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
Jihwan Oh, Soowon Oh, Murad Aghazada +3
Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specific characters. However, identi…
Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback
Yongjin Yang, Sinjae Kang, Juyong Lee +3
Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. Howe…
Self-Training Elicits Concise Reasoning in Large Language Models
Tergel Munkhbat, Namgyu Ho, Seo Hyun Kim +3
Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit th…
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
Gihun Lee, Minchan Jeong, Yujin Kim +4
While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents furthe…
Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL
Yongjin Yang, Sihyeon Kim, SangMook Kim +3
Incorporating unanswerable questions into EHR QA systems is crucial for testing the trustworthiness of a system, as providing non-existent responses can mislead doctors in their di…
FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning
Seongyoon Kim, Gihun Lee, Jaehoon Oh +1
Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data het…
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
Yongjin Yang, Joonkee Kim, Yujin Kim +3
With the proliferation of social media, accurate detection of hate speech has become critical to ensure safety online. To combat nuanced forms of hate speech, it is important to id…
Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models
Yujin Kim, Jaehong Yoon, Seonghyeon Ye +4
The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquir…
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
Taehyeon Kim, Joonkee Kim, Gihun Lee +1
While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructio…