2 citations · 3 across the 15 of their papers we have counts for
17 papers
Personalized Privacy Control in LLMs via Attention Head Intervention
Junseok Kim, Nakyeong Yang, Kyomin Jung
The rise of agentic AI enables LLMs to access diverse user data, raising critical privacy concerns. Prior work on contextual privacy studies whether LLMs regulate information discl…
Persona Switch: Mixing Distinct Perspectives in Decoding Time
Junseok Kim, Nakyeong Yang, Kyomin Jung
Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improv…
Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
Junseok Kim, Nakyeong Yang, Kyungmin Min +1
Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by ad…
Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
Sangmook Lee, Dohyung Kim, Hyukhun Koh +2
Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the e…
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
Minsung Kim, Dong-Kyum Kim, Jea Kwon +3
Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, mo…
Avoidance Decoding for Diverse Multi-Branch Story Generation
Kyeongman Park, Nakyeong Yang, Kyomin Jung
Large Language Models (LLMs) often generate repetitive and monotonous outputs, especially in tasks like story generation, due to limited creative diversity when given the same inpu…
Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
Nakyeong Yang, Dong-Kyum Kim, Jea Kwon +3
Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risk…
Bilinear representation mitigates reversal curse and enables consistent model editing
Dong-Kyum Kim, Minsung Kim, Jea Kwon +2
The reversal curse--a language model's inability to infer an unseen fact "B is A" from a learned fact "A is B"--is widely considered a fundamental limitation. We show that this is…
Rethinking Post-Unlearning Behavior of Large Vision-Language Models
Minsung Kim, Nakyeong Yang, Kyomin Jung
Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising critical privacy concerns. Machine unlearni…
FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
Nakyeong Yang, Minsung Kim, Seunghyun Yoon +2
Various studies have attempted to remove sensitive or private knowledge from a language model to prevent its unauthorized exposure. However, prior studies have overlooked the compl…
Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
Junseok Kim, Nakyeong Yang, Kyomin Jung
Recent studies demonstrate that prompting a role-playing persona to an LLM improves reasoning capability. However, assigning an adequate persona is difficult since LLMs are extreme…
Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
Nakyeong Yang, Jiwon Moon, Junseok Kim +2
Enabled by large-scale text corpora with huge parameters, pre-trained language models operate as multi-task experts using a single model architecture. However, recent studies have…
LongStory: Coherent, Complete and Length Controlled Long story Generation
Kyeongman Park, Nakyeong Yang, Kyomin Jung
A human author can write any length of story without losing coherence. Also, they always bring the story to a proper ending, an ability that current language models lack. In this w…
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
Nakyeong Yang, Taegwan Kang, Jungkyu Choi +2
Instruction-following language models often show undesirable biases. These undesirable biases may be accelerated in the real-world usage of language models, where a wide range of i…
MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
Nakyeong Yang, Minsung Kim, Seunghyun Yoon +2
With the explosion of multimedia content, video moment retrieval (VMR), which aims to detect a video moment that matches a given text query from a video, has been studied intensive…
Multi-View Zero-Shot Open Intent Induction from Dialogues: Multi Domain Batch and Proxy Gradient Transfer
Hyukhun Koh, Haesung Pyun, Nakyeong Yang +1
In Task Oriented Dialogue (TOD) system, detecting and inducing new intents are two main challenges to apply the system in the real world. In this paper, we suggest the semantic mul…
Task-specific Compression for Multi-task Language Models using Attribution-based Pruning
Nakyeong Yang, Yunah Jang, Hwanhee Lee +2
Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models utilize an unneces…