cs.CVNov 16, 2026

RAMP: Rethinking Multimodal Evaluation through Answer Readout Protocols

Authors: Jianye Zeng, Qiao Yikang, Duan Huang, Ziying Song

Organizations: University of Science and Technology of China · Central South University · Yanshan University

Abstract

Multimodal large language models (MLLMs) are often evaluated by converting model outputs into discrete answers. The conversion protocol determines which scores become predictions and can strongly influence the reported results. We introduce RAMP (Readout Aware Multimodal Protocol), a systematic framework that compares direct yes/no token logits, surface-form scores, and typed or reversed A/B interfaces under fixed model checkpoints and paired visual questions. On 500 POPE adversarial questions, typed versus bare readout changes accuracy by −20.2-20.2 percentage points for SmolVLM-256M, −16.4-16.4 for TinyLLaVA-1.1B, and +1.8+1.8 for Qwen2.5-VL-3B. Paired transitions reveal extensive prediction changes even when the net accuracy difference is small: 79 of 104 binary ChartQA items change correctness for SmolVLM-500M, despite a +1.0+1.0-point net difference. We further analyze prompt wording, candidate forms, option position, cross-task effects, and calibration. An independent offline replay reproduces 16,140 first-token decisions from saved raw scores with exact agreement. Our findings establish answer readout as a measurable component of multimodal evaluation and provide a reproducible protocol for analyzing model comparisons.

Figures & tables

Explore similar work

Nov 2, 2026

Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks

Every multimodal-LLM multiple-choice benchmark ends with a scoring rule that converts a model's response, often free-form text rather than a clean option letter, into a right/wrong verdict, buried in its code. Unlike the dataset, this rule is chosen without justification and left unexamined, yet it sets the published number. We reproduce the official scorers of eight peer-reviewed benchmarks on five open vision-language models (VLMs) that fit a single 16 GB GPU, and introduce a blinded human-plus-LLM-judge adjudication (Cohen's kappa=0.956) that recovers what the model actually answered. The scoring rule alone moves accuracy by up to 22 points on identical outputs, yet exactly 0 wherever a model emits clean option letters, so it hides on strong-model leaderboards. It is the fallback and not the rambling that does the damage: the benchmark with the highest non-compliance we measure has an artifact of exactly zero, because its scorer abstains instead of guessing; a reasoning model with non-compliance 0.000 still swings 9.5 points with which regex match of its trace the parser keeps. No standard rule is reliable: snapping a non-answer to its closest option credits answers never given yet buries correct ones, abstention discards answers stated in words, and likelihood scoring follows answer-token priors, so a single grade conflates capability with luck rather than measuring either. We release all code, labels, and the protocol, and argue benchmarks should report a non-compliance rate and at least two rules, not one unexamined grade.
Mar 3, 2026

Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory

Multimodal Large Language Models (MLLMs) have recently emerged as general architectures capable of reasoning over diverse modalities. Benchmarks for MLLMs should measure their ability for cross-modal integration. However, current benchmarks are filled with shortcut questions, which can be solved using only a single modality, thereby yielding unreliable rankings. For example, in vision-language cases, we can find the correct answer without either the image or the text. These low-quality questions unnecessarily increase the size and computational requirements of benchmarks. We introduce a multi-modal and multidimensional item response theory framework (M3IRT) that extends classical IRT by decomposing both model ability and item difficulty into image-only, text-only, and cross-modal components. M3IRT estimates cross-modal ability of MLLMs and each question's cross-modal difficulty, enabling compact, high-quality subsets that better reflect multimodal reasoning. Across 24 VLMs on three benchmarks, M3IRT prioritizes genuinely cross-modal questions over shortcuts and preserves ranking fidelity even when 50% of items are artificially generated low-quality questions, thereby reducing evaluation cost while improving reliability. M3IRT thus offers a practical tool for assessing cross-modal reasoning and refining multimodal benchmarks.
Jun 24, 2026

Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models

Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling changes the answer, a baseline reliability property called for by emerging AI evaluation guidelines. We introduce Facet-Probe, a five-facet audit (option, evidence-chunk, document-rank, image-set, and mixed-modality ordering) of 18 frontier and open-weight MLLMs. A Bayesian item-response model separates ordering noise from per-facet bias, and a same-ordering control estimates the decoder-stochastic floor for observed flips. We find that none of the 18 MLLMs we audit are order-invariant: screened per-facet panel-mean flip rates span 24-50%. A Gemini same-ordering control at temperature 0 estimates a substantial ordering excess over a same-input decoder-noise floor in verified cells. Capability predicts but does not eliminate flips; the best model still flips on 13.4% of trials. In our Gemini mitigation tests, training-free prompt changes are modality-conditional and do not transfer from text to visual reasoning. These results suggest that prompt-level mitigation alone is unlikely to provide general order robustness, motivating future work on training-time and architectural approaches. We propose cross-ordering flip rate as a standard reporting axis for MLLMs.