AI Paper Atlas

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

Operationalising the Superficial Alignment Hypothesis via Task Complexity

Tomás Vergara Browne, Darshan Patil, Ivan Titov, Siva Reddy, Tiago Pimentel, Marius Mosbach

ICML 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 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
adapt pre-trained model with a short program (a few kilobits)Olmo3-32B · GSM8Kaccuracy (%): 29.6 -> 72.2Improved
adapt pre-trained model with a short programOlmo3-7B · FLORES English-FrenchBLEU: 22.63 -> 34.43Improved
enlarge program from ImageNet-image size to the largest programs (ablation)Olmo3-32B · GSM8Kaccuracy (%): 78.4%No clear effect
add pre-training versus random initialisation (ablation)Olmo3-7B · GSM8Kaccuracy (%): 1.1% -> 67.6%Improved
add pre-training versus random initialisation (ablation)Olmo3-7B · IFEvalscore (%): 26.6% -> 68.5%Improved
add post-training on top of pre-trained checkpoint (ablation)SmolLM3 3B · GSM8Kaccuracy (%): 58.4% -> 82.8%Improved
add post-training on top of pre-trained checkpoint (ablation)SmolLM3 3B · IFEvalscore (%): 49.6% -> 70.5%Improved
add post-training to reduce program length needed for max performance (ablation)Olmo3-7B · GSM8Kprogram length (bits): 5 × 10^6 bits -> minimal effect beyond 10^4 bitsImproved
use output-layer linear projection fine-tuning instead of Pareto methods (ablation)Chen et al. linear projection · GSM8K (Olmo3-7B)accuracy vs program lengthHurt
increase program length from 10^5 bits for pre-trained checkpoints (ablation)pre-trained checkpoints · GSM8K and IFEvalaccuracyImproved

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