Papers › ILLUME: Rationalizing Vision-Language Models through Human Interactions

ILLUME: Rationalizing Vision-Language Models through Human Interactions

17 Aug 2022arXiv:2208.08241archive 2025-07-28

Manuel Brack, Patrick Schramowski, Björn Deiseroth, Kristian Kersting

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely align with user's rationales for specific answers. In order to improve this alignment and reinforce commonsense reasons, we propose a tuning paradigm based on human interactions with machine-generated data. Our ILLUME executes the following loop: Given an image-question-answer prompt, the VLM samples multiple candidate rationales, and a human critic provides feedback via preference selection, used for fine-tuning. This loop increases the training data and gradually carves out the VLM's rationalization capabilities that are aligned with human intent. Our exhaustive experiments demonstrate that ILLUME is competitive with standard supervised finetuning while using significantly fewer training data and only requiring minimal feedback.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ml-research/ILLUME officialmentioned in papermentioned on GitHubpytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningQuestion AnsweringVisual Commonsense ReasoningVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections