Grzegorz Chrupała

Why they matter

Researcher with public evidence across AI research.

AI signals
2
past 30d
Sources
2
distinct domains
Discusiones
2
past 30d
Latest signal
8d ago
View every signal from Grzegorz Chrupała →
Speech • Language • Learning https://grzegorz.chrupala.me @ Tilburg University

Articles & links

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe At #EMNLP2026 @emnlpmeeting.bsky.social, @gaofeishen.com presents our poster tomorrow (Sun 25 Oct), 16:00–17:30, Hall H, Poster Session B. 📄 https://aclanthology.org/2026.emnlp-main.654/

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe aclanthology.org
AI Weekly's analysis →
  • The paper argues standard decoding probes can't directly compare feature contributions and are distorted by feature correlations.
  • The Encoding Probe reverses direction and reconstructs transformer internal states from interpretable features spanning acoustics, phonetics, syntax, lexicon and speaker identity.
  • Speaker-related effects vary strongly across training objectives and datasets, while syntactic and lexical features contribute independently to reconstruction.
Read full analysis →
View on Bluesky · ♥ 10 ↻ 4 ↩ 0 · 2 from the directory shared this · 8d ago

In Grzegorz Chrupała's orbit

Center = Grzegorz Chrupała. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.

Are you Grzegorz Chrupała? Show it.

Add the Who’s Who of AI badge to your site or bio. It links back to this profile.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/grzegorz-chrupala-me)