arXiv:2610. 11584v1 Announce Type: cross Abstract: To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $\psi(Z)$ in place of $Z$.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
The paper introduces embedded Conditional Independence Tests (eCITs) to assess whether large language model (LLM) outputs contain additional information about an attribute beyond the source text. By embedding the source and output texts and applying existing CITs to these representations, the authors show that the null hypothesis can transfer from the original variables to their embeddings under sufficient conditions. Using a semi‑synthetic simulation design, they evaluate type I error control and power, and apply eCITs to German Parliament speeches, finding that LLM summaries reveal speaker faction and gender information beyond the original speech content.
arXiv:2609.36307v1 Announce Type: new Abstract: Partial Least Squares (PLS) regression extracts a few outcome-aligned directions in a high-dimensional X and is widely used across applied science, but...
arXiv:2511. 11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding $e$ decomposes as $\tilde e + \mu$, where the mean $\mu$ is near-identical across all sentences.
The paper introduces Conditional Predictive Sufficient Statistics (CPSS) as a formal way to capture useful visual representations that preserve latent factors shared with future data while discarding noise. It shows that predicting the next image patch embedding with a cosine loss approximates maximum likelihood under a von Mises-Fisher model, and that stop‑gradient alone does not enforce sufficiency. Experiments on MNIST and CIFAR‑10 with small causal Transformers demonstrate that CPSS readouts outperform intermediate blocks, while removing stop‑gradient collapses embedding rank even when the pretext loss appears perfect.
arXiv:2504. 12594v2 Announce Type: replace Abstract: Conditional independence testing is a critical component of feature screening, invariant statistical models, and causal discovery.
arXiv:2609.22337v1 Announce Type: cross Abstract: Linear probing is the standard instrument for detecting social biases in the hidden representations of large language models. Yet reported probe accu...