activity
20242026
collaborators

14 papers

cs.LG2026

LLMs Get Lost in Evolving User Intent

Jihoon Tack, Philippe Laban, Jennifer Neville

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inhere…

cs.LG2026

Persona-Pruner: Sculpting Lightweight Models for Role-Playing

Jinsu Kim, Jihoon Tack, Noah Lee +1

Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user perso…

cs.LG2026

Beyond Correctness: Learning Robust Reasoning via Transfer

Hyunseok Lee, Soheil Abbasloo, Jihoon Tack +1

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure t…

cs.CL2025

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

Dongjun Lee, Juyong Lee, Kyuyoung Kim +4

Recent advances in large language models (LLMs) have led to a growing interest in developing LLM-based agents for automating web tasks. However, these agents often struggle with ev…

cs.AI2025

Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions

Junbeom Kim, Kyuyoung Kim, Jihoon Tack +2

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on…

cs.LG2025

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification

Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim +2

Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs)…