The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2607. 29064v1 Announce Type: cross Abstract: Police crash narratives contain information that may supplement structured crash databases, but manual review is labor-intensive and it remains unclear how well large language models (LLMs) reproduce official crash coding.
The paper presents a decision‑aware framework for predicting dementia‑related crash severity that emphasizes auditability and selective deferral. Using 4,781 Texas crash records, the authors evaluate several models—including structured, narrative, fusion, calibrated fusion, BERT‑family, and local large‑language‑model baselines—under a stratified 70/15/15 split. The leakage‑controlled Gemma model achieves the highest macro‑F1 of 0.545, while a calibrated fusion model reaches 0.522 macro‑F1 with an expected calibration error of 0.033; selective deferral further improves performance, raising macro‑F1 to 0.573 at 70% coverage and reducing severity cost to 0.577.
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
arXiv:2608. 05064v1 Announce Type: cross Abstract: Small open-weight language models increasingly run in private, offline, and cost-sensitive settings, where the key deployment question is not only what a model answers but when it should defer to a human.
VeriPhy is an auditable physical‑verification system that evaluates generated video by compiling prompts into typed physical obligations and a statically validated execution plan before any frames are observed. During execution, it gates calls to frozen low‑level experts (e.g., segmentation, tracking, counting, depth, OCR, audio‑event detection) and returns provenance‑carrying evidence records, which are mapped to a three‑valued state (supported, contradicted, unknown) with full traceability. On a 1,500‑clip corpus of human‑annotated flaw records, VeriPhy accounts for 228 failures out of 304, outperforming a published question‑decomposition evaluator that accounts for 164, while also providing auditable evidence for each verdict.