No article text was recorded for this version.
training data attribution
Version 1 of 149 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
- Blog: Influenciæ: A Library for Tracing the Influence Back to the Data-Points
- Blog: TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
- Blog: Data Glitches Discovery using Influence-based Model Explanations
- Blog: LLMs and Copyright Risks: Benchmarks and Mitigation Approaches
- Blog: Interpretable Data-Based Explanations for Fairness Debugging
- Blog: Visual Explanation of Evidence with Additive Classifiers
- Blog: Error Discovery By Clustering Influence Embeddings
- Blog: Finding Influential Training Samples for Gradient Boosted Decision Trees
- Blog: Understanding Black-box Predictions via Influence Functions
- Blog: Correcting Large Language Model Behavior via Influence Function
- Blog: On Support Samples of Next Word Prediction
- Blog: Tracin in Semantic Segmentation of Tumor Brains in MRI, an Extended Approach (SHORT PAPER)
- Blog: Social Commonsense for Explanation and Cultural Bias Discovery
- Blog: One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
- Blog: Representer Point Selection for Explaining Regularized High-dimensional Models
- Blog: Foundation Models and Fair Use
- Blog: Convergent Approaches to AI Explainability for HEP Muonic Particles Pattern Recognition
- Blog: Contrastive Error Attribution for Finetuned Language Models
- Blog: Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
- Blog: ToxiSight: Insights Towards Detected Chat Toxicity
- Blog: LLM Attributor: Interactive Visual Attribution for LLM Generation
- Blog: A Bayesian Information-Theoretic Approach to Data Attribution
- Blog: Test of Time: Rethinking Temporal Signal of Benchmark Contamination
- Blog: Interpreting Black Box Predictions using Fisher Kernels
- Blog: Understanding Programmatic Weak Supervision via Source-aware Influence Function
- Blog: SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
- Blog: Relabeling Minimal Training Subset to Flip a Prediction
- Blog: IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection
- Blog: Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers
- Blog: dattri: A Library for Efficient Data Attribution
- Blog: HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation
- Blog: Estimating Training Data Influence by Tracing Gradient Descent
- Blog: Barriers to Counterfactual Credit Attribution for Autoregressive Models
- Blog: Towards Trustworthy LLMs for Code: A Data-Centric Synergistic Auditing Framework
- Blog: The Echoes of Multilinguality: Tracing Cultural Value Shifts during Language Model Fine-tuning
- Blog: Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
- Blog: Evaluating Data Influence in Meta Learning
- Blog: Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models
- Blog: Enhancing Trustworthiness of Fine-Tuned LLMs via Regularized Subset Selection
- Blog: PUMA: Performance Unchanged Model Augmentation for Training Data Removal
- Blog: TimeInf: Time Series Data Contribution via Influence Functions
- Blog: Theoretical and Practical Perspectives on what Influence Functions Do
- Blog: Efficient Estimation of Influence of a Training Instance
- Blog: Data Management Opportunities for Foundation Models
- Blog: Dissecting Misalignment of Multimodal Large Language Models via Influence Function
- Blog: Dissecting Representation Misalignment in Contrastive Learning via Influence Function
- Blog: Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
- Blog: Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_training_data_attribution_df3ae534,
title = {training data attribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/training-data-attribution/rdr_df3ae534b44e4095b50625f3fed861bc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_training_data_attribution_df3ae534_v1,
title = {training data attribution},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/training-data-attribution/rdr_df3ae534b44e4095b50625f3fed861bc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}