Hugging Face Trending Papers

How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models

Read the original on Hugging Face Trending Papers →

The paper investigates how six naturalistic and synthetic input perturbations affect decoder‑only language models at three levels: output behavior, hidden‑state geometry, and attention‑head function. Using GPT‑2 and Qwen2.5 checkpoints, the authors analyze layerwise geometry with centered kernel alignment and intrinsic dimension, and examine attention‑head responses in GPT‑2. They find that perturbation types produce distinct metric profiles that are not fully captured by output measures and vary across checkpoints, highlighting the need for multi‑level evaluation of robustness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv Computation and Language
Sep 4

How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models

The paper investigates how six naturalistic and synthetic input perturbations affect decoder‑only language models at three levels: output behavior, hidden‑state geometry, and attention‑head function. Using GPT‑2 and Qwen2.5 checkpoints, the authors analyze layerwise geometry with centered kernel alignment and intrinsic dimension, and examine attention‑head responses in GPT‑2. They find that perturbation types produce distinct metric profiles that are not fully captured by output measures and vary across checkpoints, highlighting the need for multi‑level evaluation of robustness.

By Dun Li Chan, Emily Liu, Niyathi Allu, Christian Hoang
arXiv AI
Aug 25

Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion

The study investigates how lexical perturbations—such as keyboard noise, character swaps, and filler insertion—affect large language models (LLMs) on reasoning benchmarks. Four open-weight instruction-tuned models and frontier models were evaluated, revealing that character-level perturbations significantly reduce accuracy, especially on multi-step reasoning tasks, while filler insertion has minimal impact. The authors attribute this asymmetry to Attention Diversion, where fragmented subword tokenization draws disproportionate attention in middle and final transformer layers; they demonstrate that both token content and attention allocation are coupled, making it difficult for inference-time repair strategies to fully recover performance.

By Jiaqian Zhu, Yang Zhang, Junhua Ding, Xiaowei Yu