InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline Paper • 2109.10104 • Published Sep 21, 2021 • 4
Next Reply Prediction X Dataset: Linguistic Discrepancies in Naively Generated Content Paper • 2602.19177 • Published 16 days ago • 4
Emergent Lexical Semantics in Neural Language Models: Testing Martin's Law on LLM-Generated Text Paper • 2511.21334 • Published Nov 26, 2025 • 1
Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets Paper • 2406.18239 • Published Jun 26, 2024 • 1