AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Causally Evaluating the Learnability of Formal Language Tasks

Vésteinn Snæbjarnarson, Anej Svete, Josef Valvoda, Reda Boumasmoud, Brian DuSell, Ryan Cotterell

ICML 2026 · Large language models › Language, safety and interpretability · approach: In-context learning analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use causal intervention (exact-count sampling) instead of correlational sampling to measure learnabilityLSTM and transformer trained on PFSA corpora · Parity + star-free PFSAdecomposed KLMixed
use causal instead of correlational sampling over 50-state random PFSAs (symbol-level)LSTM and transformer · Random 50-state 10-symbol PFSAsdecomposed KL: correlational KL first rises to a peak near 250 occurrences before fallingMixed
use causal instead of correlational sampling on a fixed 40-state topology with varied weightsLSTM and transformer · Fixed 40-state PFSA, state-leveldecomposed KLMixed
increase parity-state occurrence count in training corpus for LSTM versus transformerLSTM vs transformer · Parity + star-free PFSA, odd stateper-state KLMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy