4 papers
Tensor Network Datamodels for Training Data Attribution
Farzaneh Heidari, Md Rifat Arefin, Louis Jaburi +1
Datamodels predict how a model's behavior changes when different parts of its training data are included or removed. However, linear datamodels assign fixed contributions to traini…
Evaluation Awareness in Language Models: Representation, Verbalization, and Control
Farzaneh Heidari, Amin Memarian, Guillaume Rabusseau
Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behavior in deployment. This assump…
TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
Farzaneh Heidari, Guillaume Rabusseau
Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over…
Tractable Shapley Values and Interactions via Tensor Networks
Farzaneh Heidari, Chao Li, Guillaume Rabusseau
We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network…