TAGO performs sparse jailbreak optimization on audio LMs by retaining only high-gradient-energy tokens, preserving near-full ASR at 25% retention across three models.
The Twelfth International Conference on Learning Representations , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
LLMs process negation using both attention-based suppression and constructive representation mechanisms (construction dominant), with late-layer attention shortcuts explaining poor accuracy on negation tasks.
SLASH is a plug-and-play attention redistribution technique that counters attention sinks to enhance LLMs' intrinsic graph topology reconstruction without any training or fine-tuning.
GRASPrune removes 50% of parameters from LLaMA-2-7B via global gating and projected straight-through estimation, reaching 12.18 WikiText-2 perplexity and competitive zero-shot accuracy after four epochs on 512 calibration sequences.
citing papers explorer
-
How Language Models Process Negation
LLMs process negation using both attention-based suppression and constructive representation mechanisms (construction dominant), with late-layer attention shortcuts explaining poor accuracy on negation tasks.