AI Paper Atlas

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

A model of errors in transformers

Suvrat Raju, Praneeth Netrapalli

ICML 2026 · Large language models › Language, safety and interpretability · approach: Reasoning mechanisms and failure modes · 1 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 the two-parameter incomplete-gamma error formula to predict accuracy vs task complexityGemini 2.5 Flash, Gemini 2.5 Pro, DeepSeek R1 · list reversal, nested linear transformations, dynamic programming, Tower of Hanoi, multiplication, binary additionaccuracy vs complexityImproved
vanilla addition prompt with Gemini 2.5 Pro (no forced algorithm)error formula · Vanilla additionfit to formulaHurt
force Pro to follow a specific digit-decomposition algorithm in the prompt (ablation)Gemini 2.5 Pro addition · Addition with algorithmfit to formulaImproved
give an explicit algorithm in the prompt (pseudocode or least-significant-1 rule) (ablation)dynamic programming and Tower of Hanoi prompts · Tower of Hanoiaccuracy collapse at large cNo clear effect
tag digits with polynomial monomials x^k in the prompt (polynomial multiplication) (ablation)Gemini 2.5 Flash · MultiplicationaccuracyImproved
set variance exponent alpha = 1/2 instead of 1 (ablation)error formula · Nested linear transformationschi2 and q: q for Flash 13.9 -> 53Mixed
vary alpha away from 0.5 to 1.0 range (alpha<0.5 or alpha>1) (ablation)error formula · All tasks, mean chi2mean chi2: 0.49 -> 0.71 (alpha 0.25), 0.49 -> 0.61 (alpha 2)Hurt

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