PulseAugur
EN
LIVE 08:22:14

VANGUARD team wins JOKER 2026 humor ranking with LLM judges

The VANGUARD team, led by Ana-Maria Luisa Mocanu, secured first place in the JOKER 2026 Track Task 1 English competition with their IROH system. IROH utilizes a multi-stage retrieval process combining hybrid sparse-dense retrieval, cross-encoder reranking, and an ensemble of LoRA-adapted LLM judges. Key findings from their ablation studies indicate that rationale-distilled LLM judges significantly improve ranking quality, while structured hard negatives generally degrade generalization performance. AI

IMPACT Demonstrates advanced LLM techniques for information retrieval and ranking tasks, potentially influencing future search and recommendation systems.

RANK_REASON Academic paper detailing a novel system for humor ranking in a competition. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

VANGUARD team wins JOKER 2026 humor ranking with LLM judges

How we ranked this

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a novel system for humor ranking in a competition. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truic\u{a}, Elena-Simona Apostol ·

    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 first place on the leaderboard with 0.6347 MAP. Our pipeline combines hybrid sparse-d…