FELLA at CheckThat! 2026: From BM25 to Stella, a Multilingual Pipeline for Scientific Source Retrieval

Filippo Corradi Enrico De Lorenzo Buratta Luca Fantin Alessandro Sartor Lorenzo Tamburi N. Ferro

· 0 citations · 14 references

TL;DR

Results show that a retrieval-tuned bi-encoder combined with query translation can bridge most of the multilingual gap on consumer hardware, offering a practical building block for the automated verification of scientific claims on social media.

Semantic Scholar

View source

Similar papers

Team AKSH at CheckThat! 2026: Resource-Efficient Hybrid Retrieval for Multilingual Scientific Source Retrieval ,⋆⋆

Sufyan Siddiqui, Faisal Alvi, Abdul Samad · 1 citation

BoPC at CheckThat! 2026: Efficient Source Retrieval for Social Media Claims Using Two-Stage Dense and Cross-Attention Networks

Nguyen-Phuc Mac, M. Mac, Vincent Nguyen et al. · 1 citation

Awakened at CheckThat! 2026: X-IBIS: an Iterative Bi-Encoder Fine-Tuning with Hard-Negative Mining for Cross-Lingual Scientific Source Retrieval

Maria-Diana Cotelin, Ciprian-Octavian Truica, Elena-Simona Apostol · 1 citation

PEI at CheckThat! 2026: Investigating Query Normalization and Retrieve-and-Rerank Strategies for Linking Scientific Web Claims to Publications

This paper proposes a retrieve-and-rerank baseline consisting of the Harrier-27b dense retriever and the Jina cross-encoder reranker, and explores several extensions to improve the baseline, including multilingual query normalization through translation and noise removal, dense retriever and reranker fine-tuning, and l...

Farnoush Zeidi, Farnaz Zeidi, Roman Christof et al. · 1 citation

Varytrieval at CheckThat! 2026: Combining Rule-Based String Matching and Dense Retrieval for Scientific Claim Source Retrieval

Alica Hövelmeyer · 1 citation

Infraglyph at CheckThat! 2026: Deep Hybrid Multi-Stage Scientific Source Retrieval from Implicit Social Media Claims

Harsh Patel, Urvi Kava, Thomas Mandl et al. · 1 citation