conftrace_

under-trained token

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) llm fingerprinting (1) glitch token (1) weight-based indicator (1) token detection (1) tokenizer analysis (1) token embedding (1) ownership verification (1) supervised fine-tuning (1) language model (1)

Papers

UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification ACL 2025 Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models EMNLP 2024