AI Paper Atlas

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

Measuring Intent Comprehension in LLMs

Nadav Kunievsky, James Evans

ICML 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs · 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
scale up from small to large LLaMA/Gemma modelsLLaMA and Gemma 3 models · Guesstimation tasks (24 tasks, 5 domains)Intent Sensitivity: approximately 20% -> around 50%Improved
scale up to the 70B model versus the 12B Gemma modelLLaMA 3.3 70B vs Gemma 3 12B · Guesstimation tasks (24 tasks, 5 domains)Intent Comprehension IndexNo clear effect
scale up model sizeLLaMA and Gemma 3 models · Guesstimation tasks (24 tasks, 5 domains)Articulation SensitivityHurt
scale up model sizeLLaMA and Gemma 3 models · Guesstimation tasks (24 tasks, 5 domains)Meaningful Variability ShareHurt
lower sampling temperature from 1 to 0.5 or 0.2 (ablation)LLaMA and Gemma 3 models · Guesstimation tasks (24 tasks, 5 domains)Model UncertaintyImproved
scale up model size across topical domainsLLaMA 70B vs Gemma 27B · Guesstimation tasks (24 tasks, 5 domains)Intent Sensitivity by domainMixed

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