Imagen de Portada

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hu, Jinwei, Huang, Zhenglin, Yin, Xiangyu, Ruan, Wenjie, Cheng, Guangliang, Dong, Yi, Huang, Xiaowei
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
por: Li, Zhuoyun, et al.
Publicado: (2026)

Trust-Oriented Adaptive Guardrails for Large Language Models
por: Hu, Jinwei, et al.
Publicado: (2024)

Building Guardrails for Large Language Models
por: Dong, Yi, et al.
Publicado: (2024)

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
por: Hu, Jinwei, et al.
Publicado: (2026)

CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models
por: Yin, Xiangyu, et al.
Publicado: (2025)

TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models
por: Yin, Xiangyu, et al.
Publicado: (2025)

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
por: Li, Zhuoyun, et al.
Publicado: (2026)

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
por: Huang, Zhenglin, et al.
Publicado: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
por: Yi, Biao, et al.
Publicado: (2025)

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
por: Huang, Xinmiao, et al.
Publicado: (2025)

A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection
por: Wang, Fu, et al.
Publicado: (2024)

Responsible Agentic AI Requires Explicit Provenance
por: Hu, Jinwei, et al.
Publicado: (2026)

Achieving Sparse Activation in Small Language Models
por: Song, Jifeng, et al.
Publicado: (2024)

Training Language Models to Generate Text with Citations via Fine-grained Rewards
por: Huang, Chengyu, et al.
Publicado: (2024)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
por: Cao, Yuanpu, et al.
Publicado: (2023)

Fine-grained Stateful Knowledge Exploration: Effective and Efficient Graph Retrieval with Large Language Models
por: Tao, Dehao, et al.
Publicado: (2024)

FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression
por: Tian, Jiayi, et al.
Publicado: (2025)

Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models
por: Huang, Cheng Peng, et al.
Publicado: (2025)

How Contrastive Decoding Enhances Large Audio Language Models?
por: Lin, Tzu-Quan, et al.
Publicado: (2026)

FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
por: Li, Zekai, et al.
Publicado: (2024)

BlockPruner: Fine-grained Pruning for Large Language Models
por: Zhong, Longguang, et al.
Publicado: (2024)

PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models
por: Deng, Kunquan, et al.
Publicado: (2024)

Distilling Fine-grained Sentiment Understanding from Large Language Models
por: Zhang, Yice, et al.
Publicado: (2024)

Fine-grained Gender Control in Machine Translation with Large Language Models
por: Lee, Minwoo, et al.
Publicado: (2024)

Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm
por: Mo, Yuhong, et al.
Publicado: (2024)

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
por: Zhang, Xiaoyun, et al.
Publicado: (2024)

RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models
por: Hu, Xiangkun, et al.
Publicado: (2024)

From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models
por: Liu, Jinyi, et al.
Publicado: (2025)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
por: Huang, Tiansheng, et al.
Publicado: (2024)

Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming
por: Liu, Jiaxu, et al.
Publicado: (2024)

Strategy Adaptation in Large Language Model Werewolf Agents
por: Nakamori, Fuya, et al.
Publicado: (2025)

Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
por: Qi, Yi, et al.
Publicado: (2023)

Aligning Large Language Models via Fine-grained Supervision
por: Xu, Dehong, et al.
Publicado: (2024)

Mutual Information-based Representations Disentanglement for Unaligned Multimodal Language Sequences
por: Qian, Fan, et al.
Publicado: (2024)

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
por: Ma, Ziyang, et al.
Publicado: (2025)

Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
por: Jiang, Chaoya, et al.
Publicado: (2024)

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
por: Parihar, Shweta, et al.
Publicado: (2026)

Smaller Large Language Models Can Do Moral Self-Correction
por: Liu, Guangliang, et al.
Publicado: (2024)

Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion
por: Aldayel, Abeer, et al.
Publicado: (2024)

Fine-grained Hallucination Detection and Editing for Language Models
por: Mishra, Abhika, et al.
Publicado: (2024)