Copertina

Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pham, Van-Cuong, Nguyen, Thien Huu
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Lifelong Event Detection via Optimal Transport
di: Dao, Viet, et al.
Pubblicazione: (2024)

Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
di: Man, Hieu, et al.
Pubblicazione: (2026)

NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
di: Pham, Duy-Tung, et al.
Pubblicazione: (2024)

Do LLMs Really Adapt to Domains? An Ontology Learning Perspective
di: Mai, Huu Tan, et al.
Pubblicazione: (2024)

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective
di: Le, Minh, et al.
Pubblicazione: (2024)

Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach
di: Tu, Huu Tuong, et al.
Pubblicazione: (2025)

Realistic Evaluation of Toxicity in Large Language Models
di: Luong, Tinh Son, et al.
Pubblicazione: (2024)

Zero-shot Cross-lingual Transfer Learning with Multiple Source and Target Languages for Information Extraction: Language Selection and Adversarial Training
di: Ngo, Nghia Trung, et al.
Pubblicazione: (2024)

Few-Shot, No Problem: Descriptive Continual Relation Extraction
di: Thanh, Nguyen Xuan, et al.
Pubblicazione: (2025)

GloCOM: A Short Text Neural Topic Model via Global Clustering Context
di: Nguyen, Quang Duc, et al.
Pubblicazione: (2024)

Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering
di: Ngo, Nghia Trung, et al.
Pubblicazione: (2024)

When Names Disappear: Revealing What LLMs Actually Understand About Code
di: Le, Cuong Chi, et al.
Pubblicazione: (2025)

mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning
di: Ngo, Nghia Trung, et al.
Pubblicazione: (2025)

GloCTM: Cross-Lingual Topic Modeling via a Global Context Space
di: Phat, Nguyen Tien, et al.
Pubblicazione: (2026)

MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language Models
di: Ta, Tung Duong, et al.
Pubblicazione: (2025)

ToVo: Toxicity Taxonomy via Voting
di: Luong, Tinh Son, et al.
Pubblicazione: (2024)

AccurateRAG: A Framework for Building Accurate Retrieval-Augmented Question-Answering Applications
di: Nguyen, Linh The, et al.
Pubblicazione: (2025)

BERT-VBD: Vietnamese Multi-Document Summarization Framework
di: Vuong, Tuan-Cuong, et al.
Pubblicazione: (2024)

ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning
di: Man, Hieu, et al.
Pubblicazione: (2024)

Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models
di: Nguyen, Minh, et al.
Pubblicazione: (2024)

Similarity-Distance-Magnitude Activations
di: Schmaltz, Allen
Pubblicazione: (2025)

Taipan: Efficient and Expressive State Space Language Models with Selective Attention
di: Van Nguyen, Chien, et al.
Pubblicazione: (2024)

Preserving Generalization of Language models in Few-shot Continual Relation Extraction
di: Tran, Quyen, et al.
Pubblicazione: (2024)

CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers
di: Le, Anh Duc, et al.
Pubblicazione: (2025)

ViLLM-Eval: A Comprehensive Evaluation Suite for Vietnamese Large Language Models
di: Nguyen, Trong-Hieu, et al.
Pubblicazione: (2024)

ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images
di: Van Nguyen, Quan, et al.
Pubblicazione: (2024)

Detecting and Rectifying Noisy Labels: A Similarity-based Approach
di: Huu-Tien, Dang, et al.
Pubblicazione: (2025)

Whisper based Cross-Lingual Phoneme Recognition between Vietnamese and English
di: Minh, Nguyen Huu Nhat, et al.
Pubblicazione: (2025)

LLMs in Education: Novel Perspectives, Challenges, and Opportunities
di: Alhafni, Bashar, et al.
Pubblicazione: (2024)

Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
di: Vu, Hoang-Thuy-Duong, et al.
Pubblicazione: (2026)

Evaluating Large Language Model Capability in Vietnamese Fact-Checking Data Generation
di: To, Long Truong, et al.
Pubblicazione: (2024)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
di: Xu, Yixing, et al.
Pubblicazione: (2025)

SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference
di: Le, Cuong Chi, et al.
Pubblicazione: (2026)

Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval
di: Trung, Quang Hoang, et al.
Pubblicazione: (2024)

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs
di: Quang, Trung Nguyen, et al.
Pubblicazione: (2026)

Effective Context Modeling Framework for Emotion Recognition in Conversations
di: Van, Cuong Tran, et al.
Pubblicazione: (2024)

Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese
di: Nguyen, Nghia Hieu, et al.
Pubblicazione: (2026)

Phonetic Modeling of Dialectal Variation in Vietnamese Speech
di: Hoang, Quan Ngoc, et al.
Pubblicazione: (2026)

ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM
di: Pham, Hoang, et al.
Pubblicazione: (2025)

Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution
di: Zhang, Long, et al.
Pubblicazione: (2026)