mlsanityData to 14 Oct 2026

Memes-as-Replies: Can Models Select Humorous Manga Panel Responses?

arXiv 2602.15842 ↗First posted 21 Jan 2026cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Memes are a popular element of modern web communication, used not only as static artifacts but also as interactive replies within conversations. While computational research has focused on analyzing the intrinsic properties of memes, the dynamic and contextual use of memes to create humor remains an understudied area of web science. To address this gap, we introduce the Meme Reply Selection task and present MaMe-Re (Manga Meme Reply Benchmark), a benchmark of 100,000 human-annotated pairs (500,000 total annotations from 2,325 unique annotators) consisting of openly licensed Japanese manga panels and social media posts. Our analysis reveals three key insights: (1) large language models (LLMs) show preliminary evidence of capturing complex social cues such as exaggeration, moving beyond surface-level semantic matching; (2) the inclusion of visual information does not improve performance, revealing a gap between understanding visual content and effectively using it for contextual humor; (3) while LLMs can match human judgments in controlled settings, they struggle to distinguish subtle differences in wit among semantically similar candidates. These findings suggest that selecting contextually humorous replies remains an open challenge for current models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

18 of 39 references.

References · 18

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 490
  3. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 203
  4. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 202
  5. 2020SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!cited by 78
  6. 2021Detecting Harmful Memes and Their Targetscited by 78
  7. 2022Detecting and Understanding Harmful Memes: A Surveycited by 58
  8. 2023Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generationcited by 56
  9. 2023MemeCap: A Dataset for Captioning and Interpreting Memescited by 46
  10. 2024MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classificationcited by 30
  11. 2024Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioningcited by 19
  12. 2022What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memescited by 18
6 more
  1. 2017Spice up Your Chat: The Intentions and Sentiment Effects of Using Emojicited by 12
  2. 2021Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmarkcited by 12
  3. 2025One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humorcited by 12
  4. 2024MemeCraft: Contextual and Stance-Driven Multimodal Meme Generationcited by 9
  5. 2025Who's Laughing Now? An Overview of Computational Humour Generation and Explanationcited by 5
  6. 2021An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialogcited by 3

Built on by

Not cited yet.