Tag
MultiGhostBench is a multilingual benchmark for long-form LLM-generated text attribution under distribution shifts, featuring 928 books in six languages and highlighting performance degrades and no single method consistently best across settings.
This paper introduces AVShift, the first German benchmark for authorship verification under distribution shifts in genre, time, and AI-era. It evaluates feature-based, embedding-based, and LLM-based approaches, finding that temporal drift significantly impacts performance while no measurable AI-era shift is detected.
MetaKoopman proposes a Bayesian meta-learning framework for modeling nonlinear dynamics using linear latent representations via Koopman operators, enabling closed-form updates and uncertainty quantification. It is validated on autonomous truck and trailer systems under adverse winter conditions, outperforming prior methods in prediction accuracy and robustness.
This paper studies temporal knowledge graph forecasting under controlled distribution shifts using a synthetic generator that encodes recurrence, homophily, and periodicity. Experiments on seven architectures reveal signal-dependent robustness and limitations in model adaptivity to structural breaks.
SAE-FT introduces a novel fine-tuning method for CLIP models that uses sparse autoencoder constraints to regularize visual representations, improving robustness against distribution shifts while maintaining performance and enabling interpretability.