REVIEW 3 cited by
Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models
read the original abstract
Large Language Models (LLMs) and Vision-Language Models (VLMs) have achieved impressive performance across a wide range of tasks, yet they remain vulnerable to carefully crafted perturbations. In this study, we seek to pinpoint the sources of this fragility by identifying parameters and input dimensions (pixels or token embeddings) that are susceptible to such perturbations. To this end, we propose a stability measure called \textbf{FI}, \textbf{F}irst order local \textbf{I}nfluence, which is rooted in information geometry and quantifies the sensitivity of individual parameter and input dimensions. Our extensive analysis across LLMs and VLMs (from 1.5B to 13B parameters) reveals that: (I) A small subset of parameters or input dimensions with high FI values disproportionately contribute to model brittleness. (II) Mitigating the influence of these vulnerable parameters during model merging leads to improved performance.
Forward citations
Cited by 3 Pith papers
-
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
RL-trained lightweight controller using answer statistics improves trade-offs among correctness, latency, and total samples in adaptive sampling for LLM test-time scaling.
-
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Parallel-R1 uses SFT cold-start on easy math plus GRPO on hard math to instill parallel thinking in Qwen3-4B, reporting 8.4% average accuracy gains and a 42.9% AIME25 gain from a parallel-exploration scaffold.
-
CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Adding actor perplexity and multi-head critic variance as intrinsic exploration bonuses improves RLVR math reasoning accuracy by roughly +2 to +3 points on AIME benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.