PulseAugur
中
实时 08:58:00
English(EN) IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English

VANGUARD 团队凭借大语言模型裁判赢得 JOKER 2026 幽默排名赛

作者 PulseAugur 编辑部 · [1 个来源] ·

由 Ana-Maria Luisa Mocanu 领导的 VANGUARD 团队凭借其 IROH 系统在 JOKER 2026 Track Task 1 英语竞赛中荣获第一名。IROH 采用多阶段检索流程，结合了混合稀疏-密集检索、交叉编码器重排以及一系列 LoRA 适配的大语言模型裁判。他们的消融研究表明，带解释蒸馏的大语言模型裁判显著提高了排名质量，而结构化硬负例通常会降低泛化性能。 AI

影响 展示了用于信息检索和排名任务的高级大语言模型技术，可能影响未来的搜索和推荐系统。

排序理由 关于竞赛中幽默排名新颖系统的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

VANGUARD 团队凭借大语言模型裁判赢得 JOKER 2026 幽默排名赛

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
关于竞赛中幽默排名新颖系统的学术论文。[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.

完整方法见我们的编辑标准。

报道来源 [1]

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

    IROH：使用多阶段混合检索和基于Rationale蒸馏的LLM裁判对JOKER 2026 Track Task 1 English进行有洞察力的幽默排名

    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…

相关实体

相关话题