AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Large Language Models are Visual Reasoning Coordinators

Liangyu Chen, Bo Li, Sheng Shen, Jingkang Yang, Chunyuan Li, Kurt Keutzer, Trevor Darrell, Ziwei Liu

NeurIPS 2023 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 14 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
coordinate two VLMs with instruction-tuned LLM instead of averaging ensembleBLIP+OFA · A-OKVQA val (MC)accuracy: 56.6 -> 77.7Improved
instruction-tune the coordinator LLM (Cola-FT) vs 2-shot in-context (Cola-Zero)Cola · A-OKVQA val (MC)accuracy: 70.4 -> 77.7Improved
instruction-tune coordinator vs ensemble on e-SNLI-VEBLIP+OFA · e-SNLI-VE valaccuracy: 48.8 -> 81.6Improved
use Cola-Zero in-context coordination vs ensemble on OK-VQABLIP+OFA · OK-VQA valaccuracy: 39.2 -> 39.4No clear effect
add a second VLM (use both BLIP and OFA instead of one) (ablation)Cola-FT · A-OKVQA val (MC)accuracyImproved
include VLM plausible answers in addition to captions (ablation)Cola-FT · A-OKVQA val (MC)accuracyImproved
keep correct VLM answer labels at tuning and evaluation vs perturbed labels (ablation)Cola-FT · A-OKVQA val (MC)accuracyImproved
train LLM to output rationale before answer (ablation)Cola-FT · A-OKVQA val (MC)accuracy: 77.7 -> 74.3Hurt
use three different OFA sizes instead of identical models, Cola-FT vs ensemble gapCola-FT · A-OKVQA val (MC)accuracy: 46.62 -> 54.26Improved
scale number of OFA-base VLMs beyond 5 (Cola-FT) or 3 (Cola-Zero) (ablation)Cola · A-OKVQA val (MC)accuracy: 49.77% at 5 VLMsNo clear effect
use a FLAN-T5 80M coordinator (small) vs baselines (ablation)Cola-FT · A-OKVQA val (MC)accuracy: 55% -> 65%Improved

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