Copertina

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Eichin, Florian, Du, Yupei, Mondorf, Philipp, Matveev, Maria, Plank, Barbara, Hedderich, Michael A.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns
di: Hedderich, Michael A., et al.
Pubblicazione: (2025)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Reason to Rote: Rethinking Memorization in Reasoning
di: Du, Yupei, et al.
Pubblicazione: (2025)

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
di: Eichin, Florian, et al.
Pubblicazione: (2025)

Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
di: Körner, Felicia, et al.
Pubblicazione: (2026)

Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
di: Chen, Qiqi, et al.
Pubblicazione: (2024)

Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Tracing Uncertainty in Language Model "Reasoning"
di: Grünefeld, Nils, et al.
Pubblicazione: (2026)

If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models
di: Orth, Jasmin, et al.
Pubblicazione: (2025)

LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
di: Rabern, Brian, et al.
Pubblicazione: (2026)

Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling
di: Eichin, Florian, et al.
Pubblicazione: (2024)

BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
di: Mondorf, Philipp, et al.
Pubblicazione: (2025)

FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics
di: Du, Yupei, et al.
Pubblicazione: (2023)

Nonparametric Data Attribution for Diffusion Models
di: Zhao, Yutian, et al.
Pubblicazione: (2025)

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
di: Cheng, Xinyuan, et al.
Pubblicazione: (2026)

LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling
di: Mondorf, Philipp, et al.
Pubblicazione: (2026)

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
di: Bertolazzi, Leonardo, et al.
Pubblicazione: (2025)

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
di: Wei, Dennis, et al.
Pubblicazione: (2024)

Defending Deep Regression Models against Backdoor Attacks
di: Du, Lingyu, et al.
Pubblicazione: (2024)

Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
di: Schioppa, Andrea
Pubblicazione: (2024)

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
di: Lin, Jinxu, et al.
Pubblicazione: (2024)

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

Enhancing Training Data Attribution with Representational Optimization
di: Sun, Weiwei, et al.
Pubblicazione: (2025)

Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data
di: Su, Yiheng, et al.
Pubblicazione: (2023)

Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
di: Matsuno, Ryuta
Pubblicazione: (2024)

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
di: Zheng, Guanhua, et al.
Pubblicazione: (2025)

Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning
di: Mondorf, Philipp, et al.
Pubblicazione: (2025)

Training Data Attribution via Approximate Unrolled Differentiation
di: Bae, Juhan, et al.
Pubblicazione: (2024)

Intriguing Properties of Data Attribution on Diffusion Models
di: Zheng, Xiaosen, et al.
Pubblicazione: (2023)

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
di: Murata, Naoki, et al.
Pubblicazione: (2026)

Training Feature Attribution for Vision Models
di: Bacha, Aziz, et al.
Pubblicazione: (2025)

UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding
di: Fang, Yi, et al.
Pubblicazione: (2024)

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
di: Aerni, Michael, et al.
Pubblicazione: (2024)

Bayesian Surrogate Training on Multiple Data Sources: A Hybrid Modeling Strategy
di: Reiser, Philipp, et al.
Pubblicazione: (2024)

Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
di: Covert, Ian, et al.
Pubblicazione: (2024)

Hybrid Attribution Priors for Explainable and Robust Model Training
di: Zhang, Zhuoran, et al.
Pubblicazione: (2025)

Efficient Ensembles Improve Training Data Attribution
di: Deng, Junwei, et al.
Pubblicazione: (2024)

Exploring Training Data Attribution under Limited Access Constraints
di: Zhang, Shiyuan, et al.
Pubblicazione: (2025)