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…
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Thibaud Ardoin, Jonas Schäfer, Gerhard Wunder
Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recognition of their outputs. We de…
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…