2 citations · 5 across the 12 of their papers we have counts for
3 papers · 1 filter
Prompt Compression via Activation Aggregation
Thibaud Ardoin, Semira Einsele, Evis Bregu +1
Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant information contained in an…
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
Jonas Schäfer, Cezary Pilaszewicz, Gerhard Wunder
This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhanc…
Transparent Neighborhood Approximation for Text Classifier Explanation
Yi Cai, Arthur Zimek, Eirini Ntoutsi +1
Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to impr…