arXiv AI
Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 29
Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
arXiv:2607. 25633v1 Announce Type: cross Abstract: Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse.
arXiv Machine Learning
Jul 15
RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
arXiv:2505. 12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification.
arXiv AI
Sep 1
The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics
The study investigates how different prompt components affect language model responses in psychometric tests. By crossing five distinct baseline personas with five variants of each prompt element—persona wording, task instruction, item wording, and option symbol—the authors measure response shifts using the 1‑Wasserstein distance. Their analysis of 13 small open‑weight language models on the Big Five Inventory and Short Dark Triad reveals that task instruction and option symbol changes often cause more variation than paraphrasing the persona or item, with prompt artifacts explaining over 50% of the variation for many items.
arXiv AI
Sep 10
Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language Models
arXiv:2605.30381v2 Announce Type: replace-cross Abstract: When a language model is fine-tuned to produce systematically incorrect responses, does this training leave a structured, linearly recoverabl...
arXiv AI
Jul 2
Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation
arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.
arXiv Computation and Language
Oct 7
Are Language Models Script-Aware?
arXiv:2610.08037v1 Announce Type: new Abstract: Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research ha...