Tootfinder

Mixture of Encoders is a vector-native alternative that models both structured and unstructured data in a unified embedding space. Join Filip Makraduli as he introduces the method, demonstrates how it powers natural language search and real-time recommendations, and shares open-source tools and benchmarks for replacing complex hybrid stacks.
Learn more:

QUST_NLP at SemEval-2025 Task 7: A Three-Stage Retrieval Framework for Monolingual and Crosslingual Fact-Checked Claim Retrieval
Youzheng Liu, Jiyan Liu, Xiaoman Xu, Taihang Wang, Yimin Wang, Ye Jiang
https://arxiv.org/abs/2506.17272

QUST_NLP at SemEval-2025 Task 7: A Three-Stage Retrieval Framework for Monolingual and Crosslingual Fact-Checked Claim Retrieval
This paper describes the participation of QUST_NLP in the SemEval-2025 Task 7. We propose a three-stage retrieval framework specifically designed for fact-checked claim retrieval. Initially, we evaluate the performance of several retrieval models and select the one that yields the best results for candidate retrieval. Next, we employ multiple re-ranking models to enhance the candidate results, with each model selecting the Top-10 outcomes. In the final stage, we utilize weighted voting to deter…

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Wuwei Zhang, Fangcong Yin, Howard Yen, Danqi Chen, Xi Ye
https://arxiv.org/abs/2506.09944

Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
Recent work has identified retrieval heads (Wu et al., 2025b), a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their copy-paste behavior in Needle-in-a-Haystack tasks. In this paper, we introduce QRHEAD (Query-Focused Retrieval Head), an improved set of attention heads that enhance retrieval from long context. We identify QRHEAD by aggregating attention scores with respect to the input query, using a handful of exa…

CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
Junze Chen, Xinjie Yang, Cheng Yang, Junfei Bao, Zeyuan Guo, Yawen Li, Chuan Shi
https://arxiv.org/abs/2506.17281

CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models
Recommender systems (RSs) are designed to retrieve candidate items a user might be interested in from a large pool. A common approach is using graph neural networks (GNNs) to capture high-order interaction relationships. As large language models (LLMs) have shown strong capabilities across domains, researchers are exploring their use to enhance recommendation. However, prior work limits LLMs to re-ranking results or dataset augmentation, failing to utilize their power during candidate filtering…

Re-ranking 2021 NFL Draft by position: Where do Trevor Lawrence, Micah Parsons fall? https://www.nytimes.com/athletic/6400472/2025/06/05/nfl-draft-2021-micah-parsons-trevor-lawrence/

Kyle Liu is the Head of Engineering at Mercari, a second-hand e-commerce marketplace based in Japan. His team has been using Elastic Search for retrieval and DNN Learning to Rank for ranking for a long time. At #bbuzz, he will discuss how they re-architected their search system in response to developments in deep learning and LLM, and how they successfully convinced internal stakeholders to adopt new…

NR4DER: Neural Re-ranking for Diversified Exercise Recommendation
Xinghe Cheng, Xufang Zhou, Liangda Fang, Chaobo He, Yuyu Zhou, Weiqi Luo, Zhiguo Gong, Quanlong Guan
https://arxiv.org/abs/2506.06341

NR4DER: Neural Re-ranking for Diversified Exercise Recommendation
With the widespread adoption of online education platforms, an increasing number of students are gaining new knowledge through Massive Open Online Courses (MOOCs). Exercise recommendation have made strides toward improving student learning outcomes. However, existing methods not only struggle with high dropout rates but also fail to match the diverse learning pace of students. They frequently face difficulties in adjusting to inactive students' learning patterns and in accommodating individuali…

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
Arjun Rao, Hanieh Alipour, Nick Pendar
https://arxiv.org/abs/2506.00049

Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
This paper presents a comparison of embedding models in tri-modal hybrid retrieval for Retrieval-Augmented Generation (RAG) systems. We investigate the fusion of dense semantic, sparse lexical, and graph-based embeddings, focusing on the performance of the MiniLM-v6 and BGE-Large architectures. Contrary to conventional assumptions, our results show that the compact MiniLM-v6 outperforms the larger BGE-Large when integrated with LLM-based re-ranking within our tri-modal hybrid framework. Experim…

Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
Pascal J. Sager, Ashwini Kamaraj, Benjamin F. Grewe, Thilo Stadelmann
https://arxiv.org/abs/2505.23250

Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition, which focuses on retrieving relevant scientific literature for given social media posts. To address this task, we propose a hybrid retrieval pipeline that combines lexical precision, semantic generalization, and deep contextual re-ranking, enabling robust retrieval that bridges the informal-to-formal language gap. Specifically, we combine BM25-based keyword matching with a F…

RMIT-ADM S at the SIGIR 2025 LiveRAG Challenge
Kun Ran, Shuoqi Sun, Khoi Nguyen Dinh Anh, Damiano Spina, Oleg Zendel
https://arxiv.org/abs/2506.14516 https…

RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
This paper presents the RMIT--ADM+S participation in the SIGIR 2025 LiveRAG Challenge. Our Generation-Retrieval-Augmented Generation (GRAG) approach relies on generating a hypothetical answer that is used in the retrieval phase, alongside the original question. GRAG also incorporates a pointwise large language model (LLM)-based re-ranking step prior to final answer generation. We describe the system architecture and the rationale behind our design choices. In particular, a systematic evaluation…