conftrace_

training data attribution

10 papers

Explore in graph

Also known as

TDA

Co-occurring keywords

influence function (143) model interpretability (519) training datum (124) model interpretation (93) knowledge tracing (66) large language model (13587) gradient-based method (54) model debugging (24) model behavior (26) approximate unrolling (1)

Papers

LLM Attributor: Interactive Visual Attribution for LLM Generation AAAI 2025
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes CVPR 2024
Training Data Attribution via Approximate Unrolling NIPS 2024
Unlearning Traces the Influential Training Data of Language Models ACL 2024
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration EMNLP 2024
A Bayesian Approach To Analysing Training Data Attribution In Deep Learning NIPS 2023
How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning EMNLP 2023
Theoretical and Practical Perspectives on what Influence Functions Do NIPS 2023
Towards Tracing Knowledge in Language Models Back to the Training Data EMNLP 2022
Understanding Black-box Predictions via Influence Functions ICML 2017