Cover Image

SUIT: Knowledge Editing with Subspace-Aware Key-Value Mappings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Haewon, Kim, Sangwoo, Jo, Yohan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Context-Robust Knowledge Editing for Language Models
by: Park, Haewon, et al.
Published: (2025)

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
by: Park, Yoonah, et al.
Published: (2025)

Thinking Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs
by: Won, Jeongmoon, et al.
Published: (2026)

Dialogue Systems for Emotional Support via Value Reinforcement
by: Kim, Juhee, et al.
Published: (2025)

Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction
by: Park, Sejun, et al.
Published: (2026)

SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue
by: Lee, Jonggeun, et al.
Published: (2026)

In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents
by: Lee, Seungkyu, et al.
Published: (2025)

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples
by: Pyun, Haesung, et al.
Published: (2025)

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction
by: Lee, Yooseop, et al.
Published: (2025)

O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
by: Cai, Yuchen, et al.
Published: (2024)

SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents
by: Seo, Gyuhyeon, et al.
Published: (2025)

Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers
by: Heo, Chaewon, et al.
Published: (2026)

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
by: Wang, Fan, et al.
Published: (2024)

Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items
by: Han, Jongwook, et al.
Published: (2025)

Non-linear Interventions on Large Language Models
by: Kim, Sangwoo
Published: (2026)

Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
by: Chae, Kyubyung, et al.
Published: (2024)

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding
by: Song, Sangjun, et al.
Published: (2025)

Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
by: Kong, Injin, et al.
Published: (2026)

Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
by: Jin, Mingyu, et al.
Published: (2025)

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
by: Bi, Baolong, et al.
Published: (2024)

Future Policy Approximation for Offline Reinforcement Learning Improves Mathematical Reasoning
by: Oh, Minjae, et al.
Published: (2025)

ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
by: Shim, Jeonghoon, et al.
Published: (2025)

SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?
by: Lee, Jonggeun, et al.
Published: (2026)

Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model
by: Kim, Taehee, et al.
Published: (2024)

Model-based Preference Optimization in Abstractive Summarization without Human Feedback
by: Choi, Jaepill, et al.
Published: (2024)

MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
by: Xia, Shujun, et al.
Published: (2025)

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
by: Dong, Zilu, et al.
Published: (2025)

Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge
by: Sun, Zengkui, et al.
Published: (2024)

Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation
by: Yoon, Chanwoong, et al.
Published: (2024)

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
by: Kong, Injin, et al.
Published: (2026)

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
by: Choi, Yunho, et al.
Published: (2026)

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
by: Lu, Yifan, et al.
Published: (2025)

Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering
by: Deng, Lingwen, et al.
Published: (2025)

LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education
by: Weissburg, Iain, et al.
Published: (2024)

Quantifying Data Contamination in Psychometric Evaluations of LLMs
by: Han, Jongwook, et al.
Published: (2025)

An Exploration of Knowledge Editing for Arabic
by: Mousi, Basel, et al.
Published: (2025)

On the Robustness of Knowledge Editing for Detoxification
by: Dong, Ming, et al.
Published: (2026)

Editing Across Languages: A Survey of Multilingual Knowledge Editing
by: Durrani, Nadir, et al.
Published: (2025)

EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
by: Liu, Jiateng, et al.
Published: (2024)

Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
by: Lee, Jonggeun, et al.
Published: (2025)