Pith. sign in

Interpretability in the Wild: A Circuit for Indirect Object Identification in

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 1 cs.LG 1

years

2026 2

roles

background 1

polarities

background 1

representative citing papers

Emergent Semantic Role Understanding in Language Models

cs.AI · 2026-05-09 · unverdicted · novelty 5.0

Semantic role understanding partially emerges during language model pre-training, with linear probes on frozen representations achieving substantial performance that improves with scale but does not match fine-tuned models, and representations shifting toward more distributed forms at larger scales.

citing papers explorer

Showing 2 of 2 citing papers.

  • Emergent Semantic Role Understanding in Language Models cs.AI · 2026-05-09 · unverdicted · none · ref 2

    Semantic role understanding partially emerges during language model pre-training, with linear probes on frozen representations achieving substantial performance that improves with scale but does not match fine-tuned models, and representations shifting toward more distributed forms at larger scales.

  • Mechanistic Anomaly Detection via Functional Attribution cs.LG · 2026-04-21 · conditional · none · ref 60

    A grid-free attention-based deep learning model interpolates surface-level PM2.5 concentrations across the US using sparse sensor data and auxiliary geospatial features.