ru
ru
Source
NAACL
DATE OF PUBLICATION
04/29/2025
Authors
Share

Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images

Abstract

Measuring how real images look is a complextask in artificial intelligence research. For example,an image of a boy with a vacuum cleanerin a desert violates common sense. We introducea novel method, which we call Throughthe Looking Glass (TLG), to assess image commonsense consistency using Large Vision-Language Models (LVLMs) and Transformerbasedencoder. By leveraging LVLMs to extractatomic facts from these images, we obtaina mix of accurate facts. We proceed byfine-tuning a compact attention-pooling classifierover encoded atomic facts. Our TLG hasachieved a new state-of-the-art performanceon the WHOOPS! and WEIRD datasets whileleveraging a compact fine-tuning component.

Full text DOWNLOAD pdf

Similar publications

NAACL
SkipCLM: Enchancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection
Nikita Sushko, Alexander Panchenko, Elena Tutubalina
SOURCE
NAACL
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Sergey Pletenev, Maria Marina, Daniil Moskovskiy, Vasily Konovalov, Pavel Braslavski, Alexander Panchenko, Mikhail Salnikov
SOURCE
NAACL
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev, Elizaveta Goncharova, Polina Druzhinina, Ivan Oseledets,
SOURCE
NAACL
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
Artem Vazhentsev, Lyudmila Rvanova, Ivan Lazichny, Alexander Panchenko, Maxim Panov, Timothy Baldwin, Artem Shelmanov
SOURCE
NAACL
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators
Daniil Moskovskiy, Nikita Sushko, Sergey Pletenev, Alexander Panchenko, Elena Tutubalina
SOURCE
ICLR
A3D: Does Diffusion Dream about 3D Alignment?
Savva Ignatyev, Nina Konovalova, Daniil Selikhanovych, Oleg Voynov , Nikolay Patakin, Ilya Olkov, Dmitry Senushkin, Alexey Artemov, Anton Konushin, Alexander Filippov, Peter Wonka, Evgeny Burnaev
SOURCE
NAACL
SPY: Enhancing Privacy with Synthetic PII Detection Dataset
Maksim Savkin, Timur Ionov, Vasily Konovalov
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again