Researchers Create Dataset to Study How AI Understands Humorous Visual Metaphors
Computer scientists have created the Hummus Dataset, containing 1,000 annotated image-caption pairs from the New Yorker Caption Contest, to study how multimodal AI models understand humorous metaphors. The research draws on incongruity theory of humor and conceptual metaphor theory to develop a novel annotation scheme for analyzing when metaphors create humor across visual and textual information. The work reveals that current large language models struggle to integrate visual and textual information when processing humorous metaphors, highlighting a gap in AI's ability to understand complex forms of humor.
Researchers have developed a new dataset called Hummus (Humorous Multimodal Metaphor Use) to investigate how artificial intelligence systems understand humor that relies on metaphorical language combined with images. The dataset contains 1,000 expert-annotated image-caption pairs sourced from the New Yorker Caption Contest corpus. The annotation scheme was developed by combining insights from incongruity theory (which explains humor through unexpected juxtapositions), conceptual metaphor theory, and existing metaphor annotation frameworks. When tested on the dataset, state-of-the-art multimodal large language models demonstrated significant limitations in detecting and interpreting humorous multimodal metaphors, particularly when the humor required integrating information from both visual and textual elements. The researchers have made both the dataset and code publicly available to support further research in this area.
What's missing
The study does not discuss potential limitations of the annotation scheme itself, inter-annotator agreement metrics, or how the dataset's focus on New Yorker captions—a specific genre of humor—might affect generalizability to other forms of humorous multimodal metaphor use.
What different sources said
- arXiv cs.CLCenter
Re-defining Humor Data Objects for AI Humor Research
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.