AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA Benchmarks

Claudio Pinhanez, Paulo Cavalin, Cassia Sanctos, Marcelo Carpinette Grave

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 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 a medium model (llama-3.3-70b) instead of a small one (Llama-3-8B)Llama family · MMLU-Redux (10 repetitions)S/T (% SURE questions): 53% -> 98%Improved
raise inference temperature from 0.3 to 1.0 (ablation)Llama-3-8B · MMLU-Redux (10 repetitions)S/T (% SURE questions): 53% -> 11%Hurt
raise inference temperature from 0.3 to 1.0 (ablation)Llama-3-8B · MMLU-Redux (10 repetitions)RWS (right when SURE): 0.81 -> 0.94Improved
raise inference temperature from 0.3 to 1.0 (ablation)Llama-3-8B · MMLU-Redux (10 repetitions)accuracy average: 0.590 -> 0.428Hurt
raise inference temperature from 0.3 to 1.0 (ablation)medllama3-v20 · MedQA (10 repetitions)S/T (% SURE questions): 96% -> 88%Hurt
raise inference temperature from 0.3 to 1.0 (ablation)medllama3-v20 · MedQA (10 repetitions)RWS (right when SURE): 0.75 -> 0.76No clear effect
use instruct instead of base Llama-3-8BLlama-3-8B · MMLU-Redux (10 repetitions)S/T (% SURE questions): 53% -> 79%Improved
use instruct instead of base Llama-3-8BLlama-3-8B · MedQA (10 repetitions)accuracy average: 0.512 -> 0.405Hurt
medical finetuning of Mistral-7B-Instruct into BioMistral-7BMistral-7B-Instruct · MedQA (10 repetitions)accuracy average: 0.321 -> 0.371Improved
medical finetuning of llama1-7b into medalpaca-7bllama1-7b · MedQA (10 repetitions)accuracy average: 0.201 -> 0.342Improved
keep only SURE answers (filter out UNSURE) for Bio-Medical-Llama-3-8BBio-Medical-Llama-3-8B · MedQA (10 repetitions)accuracy: 0.736 -> 0.79Improved
use granite 3.1-8b-instruct instead of 3.1-8b-basegranite 8B · MMLU-Redux (10 repetitions)accuracy average: 0.575 -> 0.640Improved

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