DS@GT At TREC TOT 2025: Bridging Vague Recollection With Fusion Retrieval And Learned Reranking

Abstract

We develop a two-stage retrieval system that combines multiple complementary retrieval methods with a learned reranker and LLM-based reranking, to address the TREC Tip-of-the-Tongue (ToT) task. In the first stage, we employ hybrid retrieval that merges LLM-based retrieval, sparse (BM25), and dense (BGE-M3) retrieval methods. We also introduce topic-aware multi-index dense retrieval that partitions the Wikipedia corpus into 24 topical domains. In the second stage, we evaluate both a trained LambdaMART reranker and LLM-based reranking. To support model training, we generate 5000 synthetic ToT queries using LLMs. Our best system achieves recall of 0.66 and NDCG@1000 of 0.41 on the test set by combining hybrid retrieval with Gemini-2.5-flash reranking, demonstrating the effectiveness of fusion retrieval.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhou2026ds

Related papers

• MST-R: Multi-stage Tuning For Retrieval Systems And Metric Evaluation (2024)0.00
• Rethinking Hybrid Retrieval: When Small Embeddings And LLM Re-ranking Beat Bigger Models (2025)0.00
• Recurrence Meets Transformers For Universal Multimodal Retrieval (2025)2.41
• Rebol: Retrieval Via Bayesian Optimization With Batched LLM Relevance Observations And Query Reformulation (2026)0.00
• Deep Retrieval At Checkthat! 2025: Identifying Scientific Papers From Implicit Social Media Mentions Via Hybrid Retrieval And Re-ranking (2025)0.00
• Hyrec: Exploring Hybrid-based Retriever For Chinese (2025)0.00
• DAT: Dynamic Alpha Tuning For Hybrid Retrieval In Retrieval-augmented Generation (2025)0.00
• MARVEL: Multimodal Adaptive Reasoning-intensive Expand-rerank And Retrieval (2026)0.00