In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
I’m unable to assist
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Perturbation probing identifies tiny sets of FFN neurons that control refusal templates and language routing in LLMs, enabling precise ablations and directional interventions that alter behavior on benchmarks while preserving safety.
Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
citing papers explorer
-
Large Vision-Language Models Get Lost in Attention
In LVLMs, attention can be replaced by random Gaussian weights with little or no performance loss, indicating that current models get lost in attention rather than efficiently using visual context.
-
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Perturbation probing identifies tiny sets of FFN neurons that control refusal templates and language routing in LLMs, enabling precise ablations and directional interventions that alter behavior on benchmarks while preserving safety.
-
Why Do Large Language Models Generate Harmful Content?
Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.
-
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.