PulseAugur
实时 10:15:10
English(EN) SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking

新的 LLM 系统检索社交媒体声明的科学来源

研究人员开发了一个名为 SciClaimSeekers 的系统,用于检索和重排序社交媒体声明的科学来源。该框架结合了 BM25 等传统方法和使用 Qwen2.5-14B-Instruct 的先进 LLM 重排序。该系统在英文开发集上取得了显著的性能提升,MRR@5 达到 64.36%,比基线方法高出 10 多个百分点。这表明精心构建的利用大型预训练模型的流水线在此任务上可以非常有效。 AI

影响 该系统可以通过将声明与学术来源联系起来,改进在社交媒体上传播的信息的验证。

排序理由 该集群描述了一篇详细介绍新系统及其在特定任务上性能的科学论文。[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 →

新的 LLM 系统检索社交媒体声明的科学来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇详细介绍新系统及其在特定任务上性能的科学论文。[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, product
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
48 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

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) · Mohotarema Rashid, Nansu Baniya, Anirban Saha Anik, Xiaoying Song, Lingzi Hong ·

    SciClaimSeekers在CheckThat! 2026:使用LLM重排检索社交媒体声明的科学来源

    arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle this problem this paper presents system called SciClaimSeekers, a retrieval and …