By cryptoadmin 
Might 14, 2025
The GIST Editors' notes
This text has been reviewed in line with Science X's editorial course of and insurance policies. Editors have highlighted the next attributes whereas making certain the content material's credibility:
fact-checked
preprint
trusted supply
proofread
Imaginative and prescient-language fashions can't deal with queries with negation phrases, examine reveals
Think about a radiologist analyzing a chest X-ray from a brand new affected person. She notices the affected person has swelling within the tissue however doesn’t have an enlarged coronary heart. Trying to pace up prognosis, she would possibly use a vision-language machine-learning mannequin to seek for studies from related sufferers.
But when the mannequin mistakenly identifies studies with each circumstances, the most probably prognosis may very well be fairly totally different: If a affected person has tissue swelling and an enlarged coronary heart, the situation may be very more likely to be cardiac-related, however with no enlarged coronary heart there may very well be a number of underlying causes.
In a brand new examine showing on the arXiv preprint server, MIT researchers have discovered that vision-language fashions are extraordinarily more likely to make such a mistake in real-world conditions as a result of they don't perceive negation—phrases like "no" and "doesn't" that specify what is fake or absent.
"These negation phrases can have a really important influence, and if we’re simply utilizing these fashions blindly, we might run into catastrophic penalties," says Kumail Alhamoud, an MIT graduate scholar and lead writer of this examine.
The researchers examined the flexibility of vision-language fashions to establish negation in picture captions. The fashions typically carried out in addition to a random guess. Constructing on these findings, the group created a dataset of photographs with corresponding captions together with negation phrases describing lacking objects.
They present that retraining a vision-language mannequin with this dataset results in efficiency enhancements when a mannequin is requested to retrieve photographs that don’t include sure objects. It additionally boosts accuracy on a number of alternative query answering with negated captions.
However the researchers warning that extra work is required to handle the basis causes of this downside. They hope their analysis alerts potential customers to a beforehand unnoticed shortcoming that might have severe implications in high-stakes settings the place these fashions are at the moment getting used, from figuring out which sufferers obtain sure remedies to figuring out product defects in manufacturing vegetation.
"This can be a technical paper, however there are greater points to contemplate. If one thing as basic as negation is damaged, we shouldn't be utilizing massive imaginative and prescient/language fashions in lots of the methods we’re utilizing them now—with out intensive analysis," says senior writer Marzyeh Ghassemi, an affiliate professor within the Division of Electrical Engineering and Pc Science (EECS) and a member of the Institute of Medical Engineering Sciences and the Laboratory for Data and Choice Techniques.
Ghassemi and Alhamoud are joined on the paper by Shaden Alshammari, an MIT graduate scholar; Yonglong Tian of OpenAI; Guohao Li, a former postdoc at Oxford College; Philip H.S. Torr, a professor at Oxford; and Yoon Kim, an assistant professor of EECS and a member of the Pc Science and Synthetic Intelligence Laboratory (CSAIL) at MIT. The analysis shall be offered on the Convention on Pc Imaginative and prescient and Sample Recognition.
Neglecting negation
Imaginative and prescient-language fashions (VLM) are educated utilizing big collections of photographs and corresponding captions, which they be taught to encode as units of numbers, referred to as vector representations. The fashions use these vectors to tell apart between totally different photographs.
A VLM makes use of two separate encoders, one for textual content and one for photographs, and the encoders be taught to output related vectors for a picture and its corresponding textual content caption.
"The captions categorical what’s within the photographs—they’re a constructive label. And that’s really the entire downside. Nobody appears at a picture of a canine leaping over a fence and captions it by saying 'a canine leaping over a fence, with no helicopters,'" Ghassemi says.
As a result of the image-caption datasets don't include examples of negation, VLMs by no means be taught to establish it.
To dig deeper into this downside, the researchers designed two benchmark duties that take a look at the flexibility of VLMs to know negation.
For the primary, they used a big language mannequin (LLM) to re-caption photographs in an present dataset by asking the LLM to consider associated objects not in a picture and write them into the caption. Then they examined fashions by prompting them with negation phrases to retrieve photographs that include sure objects, however not others.
For the second process, they designed a number of alternative questions that ask a VLM to pick out essentially the most acceptable caption from a listing of carefully associated choices. These captions differ solely by including a reference to an object that doesn't seem within the picture or negating an object that does seem within the picture.
The fashions typically failed at each duties, with picture retrieval efficiency dropping by almost 25% with negated captions. When it got here to answering multiple-choice questions, the very best fashions solely achieved about 39% accuracy, with a number of fashions acting at and even beneath random probability.
One cause for this failure is a shortcut the researchers name affirmation bias—VLMs ignore negation phrases and deal with objects within the photographs as a substitute.
"This doesn’t simply occur for phrases like 'no' and 'not." No matter the way you categorical negation or exclusion, the fashions will merely ignore it," Alhamoud says.
This was constant throughout each VLM they examined.
'A solvable downside'
Since VLMs aren't usually educated on picture captions with negation, the researchers developed datasets with negation phrases as a primary step towards fixing the issue.
Utilizing a dataset with 10 million image-text caption pairs, they prompted an LLM to suggest associated captions that specify what’s excluded from the pictures, yielding new captions with negation phrases.
They needed to be particularly cautious that these artificial captions nonetheless learn naturally, or it might trigger a VLM to fail in the actual world when confronted with extra complicated captions written by people.
They discovered that fine-tuning VLMs with their dataset led to efficiency features throughout the board. It improved fashions' picture retrieval talents by about 10%, whereas additionally boosting efficiency within the multiple-choice question-answering process by about 30%.
"However our answer will not be excellent. We’re simply recaptioning datasets, a type of information augmentation. We haven't even touched how these fashions work, however we hope it is a sign that it is a solvable downside and others can take our answer and enhance it," Alhamoud says.
On the identical time, he hopes their work encourages extra customers to consider the issue they need to use a VLM to unravel and design some examples to check it earlier than deployment.
Sooner or later, the researchers might increase upon this work by instructing VLMs to course of textual content and pictures individually, which can enhance their capacity to know negation. As well as, they might develop further datasets that embrace image-caption pairs for particular functions, comparable to well being care.
Extra data: Kumail Alhamoud et al, Imaginative and prescient-Language Fashions Do Not Perceive Negation, arXiv (2025). DOI: 10.48550/arxiv.2501.09425
Journal data: arXiv Supplied by Massachusetts Institute of Expertise
This story is republished courtesy of MIT Information (net.mit.edu/newsoffice/), a preferred web site that covers information about MIT analysis, innovation and instructing.
Quotation: Imaginative and prescient-language fashions can't deal with queries with negation phrases, examine reveals (2025, Might 14) retrieved 15 Might 2025 from https://techxplore.com/information/2025-05-vision-language-queries-negation-words.html This doc is topic to copyright. Other than any honest dealing for the aim of personal examine or analysis, no half could also be reproduced with out the written permission. The content material is supplied for data functions solely.
Discover additional
Serving to pc imaginative and prescient and language fashions perceive what they see 39 shares
Feedback to editors