Cover Image

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Guanhua, Sang, Jitao, Xu, Changsheng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
by: Zhang, Jiaming, et al.
Published: (2023)

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
by: Kasmi, Gabriel, et al.
Published: (2024)

Inference-Time Rule Eraser: Fair Recognition via Distilling and Removing Biased Rules
by: Zhang, Yi, et al.
Published: (2024)

Harmony: A Unified Framework for Modality Incremental Learning
by: Song, Yaguang, et al.
Published: (2025)

DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
by: Li, Rongqing, et al.
Published: (2024)

Rethinking GSPO: The Perplexity-Entropy Equivalence
by: Liu, Chi
Published: (2025)

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
by: Wu, Shangxi, et al.
Published: (2023)

Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
by: Haxholli, Etrit, et al.
Published: (2025)

Unifying Attribution-Based Explanations Using Functional Decomposition
by: Gevaert, Arne, et al.
Published: (2024)

Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
by: Xie, Huanyi, et al.
Published: (2025)

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
by: Dai, Lu, et al.
Published: (2025)

Generalized Preference Optimization: A Unified Approach to Offline Alignment
by: Tang, Yunhao, et al.
Published: (2024)

Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering
by: Zhang, Yiqun, et al.
Published: (2026)

Momentum Point-Perplexity Mechanics in Large Language Models
by: Tomaz, Lorenzo, et al.
Published: (2025)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

Revisiting Essential and Nonessential Settings of Evidential Deep Learning
by: Chen, Mengyuan, et al.
Published: (2024)

ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
by: Zhu, Zhiyu, et al.
Published: (2025)

HMVI: Unifying Heterogeneous Attributes with Natural Neighbors for Missing Value Inference
by: Luo, Xiaopeng, et al.
Published: (2026)

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
by: Deng, Huiqi, et al.
Published: (2025)

Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar
by: Gambardella, Andrew, et al.
Published: (2025)

A Dual-Perspective Approach to Evaluating Feature Attribution Methods
by: Li, Yawei, et al.
Published: (2023)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
by: Zhang, Shichang, et al.
Published: (2025)

Simple Multigraph Convolution Networks
by: Wu, Danyang, et al.
Published: (2024)

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
by: Zhang, Xiaoyun, et al.
Published: (2025)

EAGLE: Efficient Alignment of Generalized Latent Embeddings for Multimodal Survival Prediction with Interpretable Attribution Analysis
by: Tripathi, Aakash, et al.
Published: (2025)

Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
by: Park, Hyuntae, et al.
Published: (2025)

Preference Learning for AI Alignment: a Causal Perspective
by: Kobalczyk, Katarzyna, et al.
Published: (2025)

The Alignment Problem from a Deep Learning Perspective
by: Ngo, Richard, et al.
Published: (2022)

Dissecting Quantization Error: A Concentration-Alignment Perspective
by: Federici, Marco, et al.
Published: (2026)

A Comprehensive Survey on Evidential Deep Learning and Its Applications
by: Gao, Junyu, et al.
Published: (2024)

Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
by: Xiao, Yao, et al.
Published: (2025)

AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
by: Zhang, Jiaming, et al.
Published: (2024)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
by: Shivagunde, Namrata, et al.
Published: (2026)

Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings
by: Skrodzki, Martin, et al.
Published: (2023)

Probe-Based Data Attribution: Discovering and Mitigating Undesirable Behaviors in LLM Post-Training
by: Xiao, Frank, et al.
Published: (2026)

Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
by: Zhang, Chuyifei, et al.
Published: (2026)

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
by: Chuang, Yung-Sung, et al.
Published: (2025)

A Unified Model for Spatio-Temporal Prediction Queries with Arbitrary Modifiable Areal Units
by: Chen, Liyue, et al.
Published: (2024)

Greed is Good: A Unifying Perspective on Guided Generation
by: Blasingame, Zander W., et al.
Published: (2025)

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
by: Scholten, Yan, et al.
Published: (2024)