arXiv AI June 2, 2026 By Alexey Tikhonov, Alexey Ivanov

lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation

arXiv:2606. 00022v1 Announce Type: cross Abstract: Humor generation remains difficult not only because producing fluent, novel jokes is hard, but because "funny" is audience-dependent and supervision is noisy -- preferences vary with audience, context, and culture, and annotator agreement is often low.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv AI

Jul 16

RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar

arXiv:2607. 13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chinese).

By Marek \v{S}uppa, Vikt\'oria Ondrejov\'a, Lucia Ganajov\'a, Gregor Karetka, Daniel Skala

llms rag agents benchmarks

arXiv Computation and Language

Sep 15

HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation

arXiv:2604.09629v3 Announce Type: replace Abstract: Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective (next-token prediction)...

By Edward Ajayi, Prasenjit Mitra

llms reinforcement-learning fine-tuning efficiency safety

arXiv AI

Sep 10

Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs

arXiv:2601.03103v2 Announce Type: replace-cross Abstract: Humor preferences vary widely across individuals and cultures, complicating the evaluation of humor using large language models (LLMs). In th...

By Soichiro Murakami, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

llms

arXiv Computation and Language

Sep 15

IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English

arXiv:2609.15618v1 Announce Type: cross Abstract: Our team, VANGUARD, presents IROH (Insightful Ranking of Humor), a three-stage retrieval system for JOKER Task 1 English at CLEF 2026, achieving firs...

By Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truic\u{a}, Elena-Simona Apostol

llms rag fine-tuning benchmarks

arXiv Computation and Language

Sep 11

Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding

The paper introduces IRS (Incongruity-Resolution Supervision), a framework that breaks humor understanding into three parts: identifying mismatches in a visual scene, creating coherent reinterpretations of those mismatches, and aligning these interpretations with human preferences. IRS uses structured reasoning traces to guide models from visual perception to humorous interpretation, and it is evaluated on the New Yorker Cartoon Caption Contest. Experiments on 7B, 32B, and 72B models show that IRS improves caption matching and ranking, with the 72B model achieving 76.10% ranking accuracy—outperforming non-expert humans and all other multimodal baselines—and demonstrates transferable reasoning patterns in zero‑shot settings.

By Hatice Merve Vural, Doga Kukul, Ege Erdem Ozlu, Demir Ekin Arikan, Bob Mankoff, Erkut Erdem, Aykut Erdem

multimodal benchmarks safety

arXiv Computation and Language

Aug 25

CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension

arXiv:2608.23172v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) have demonstrated remarkable versatility across a wide range of multimodal tasks. However, understanding humo...

By Abhilash Nandy, Rahul Seetharaman, Aman Bansal, Rounak Saha, Manav Nitin Kapadnis, Millon Madhur Das, Pawan Goyal, Niloy Ganguly

llms multimodal benchmarks

One email a morning, machine-written

Related stories

RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar

HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation

Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs

IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English

Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding

CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension