pith. sign in

arXiv preprint arXiv:2311.04897 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

unclear 1

representative citing papers

Inference Time Causal Probing in LLMs

cs.AI · 2026-05-08 · unverdicted · novelty 7.0

HDMI is a new probe-free technique that steers LLM hidden states via margin objectives to achieve more reliable causal interventions than prior probe-based methods on standard benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Inference Time Causal Probing in LLMs cs.AI · 2026-05-08 · unverdicted · none · ref 13

    HDMI is a new probe-free technique that steers LLM hidden states via margin objectives to achieve more reliable causal interventions than prior probe-based methods on standard benchmarks.

  • HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory cs.AI · 2026-05-07 · unverdicted · none · ref 27

    HyperLens reveals that deeper transformer layers magnify small confidence changes into fine-grained trajectories, allowing quantification of cognitive effort where complex tasks demand more and standard SFT can reduce it.