Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time
Paper recorded by Signals 4 on 2026-09-04 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-04 on arXiv · recorded by Signals 4 on 2026-09-07
Category: cs.CL · 自然语言处理 · first seen 2026-09-07
Abstract
We propose an influence score to quantify the contribution of attention heads to classification decisions in Transformer-based models designed for prompt injection detection. The score combines directional influence on the logits with structural contribution within the residual stream, enabling a multi-scale analysis at the head, layer, and network levels. Applied to a DeBERTa model specialized fo
Read on arXiv →
Cite this page: Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time: the #113 most recent of 186 cs.CL papers we have recorded (as of 2026-09-04). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/influence-score-and-transformers-interpretability-measure-of-the-effective-impac.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free