arXiv AI September 2, 2026 By Marco Simnacher, Georg Keilbar, Benjamin K\"onig, Christoph Lippert, Sonja Greven

Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches

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.

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 AI.

arXiv Machine Learning

Oct 9

Embedding-Bias in Conditional Independence Testing

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 $Z$.

By Nikolaj Thams, Anton Rask Lundborg

llms rag safety

arXiv Machine Learning

Jun 2

The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition

arXiv:2606. 00545v1 Announce Type: new Abstract: Post-trained language models can recognize their own outputs from a sentence or two out of context.

By Asvin G

llms

arXiv AI

Jun 30

Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data

arXiv:2606. 30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias.

By Haobo Yang

llms safety

arXiv Computation and Language

Oct 7

Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation

arXiv:2610.08303v1 Announce Type: new Abstract: Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures...

By Shu-Kai Hsieh, Da-Chen Lian

llms rag benchmarks safety

arXiv AI

Aug 20

Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements

The paper introduces Debiased Inference with Multiple Imperfect Measurements (DMM), a framework that uses several error‑prone AI measurements to perform valid downstream statistical inference without requiring costly gold‑standard labels. By assuming conditional independence of the measurements given the true label and unit‑level features, DMM leverages CP decomposition and semiparametric theory to prove consistency and asymptotic normality of its estimator. Simulations demonstrate that DMM yields valid inference and can improve efficiency when additional imperfect measurements are available, and the authors provide diagnostics for the key independence assumption.

By Naoki Egami, Sooahn Shin

llms rag safety

arXiv Computation and Language

Sep 22

The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness

arXiv:2605.28190v2 Announce Type: replace Abstract: Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embeddin...

By Manuel Frank, Haithem Afli

llms rag benchmarks