# TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking

arXiv: https://arxiv.org/abs/2403.17759 · HTML: https://mlsanity.com/paper/2403.17759/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2024.

## Built on by (most cited first, 11 of 11)

- [Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation](https://mlsanity.com/paper/2409.14634/) (2024)
- [Literature-Grounded Novelty Assessment of Scientific Ideas](https://mlsanity.com/paper/2506.22026/) (2025)
- [RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers](https://mlsanity.com/paper/2403.18276/) (2024)
- [W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering](https://mlsanity.com/paper/2408.08444/) (2024)
- [RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine](https://mlsanity.com/paper/2410.18097/) (2024)
- [Distillation versus Contrastive Learning: How to Train Your Rerankers](https://mlsanity.com/paper/2507.08336/) (2025)
- [RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback](https://mlsanity.com/paper/2508.05512/) (2025)
- [LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback](https://mlsanity.com/paper/2504.01448/) (2025)
- [DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering](https://mlsanity.com/paper/2601.16478/) (2026)
- [QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort](https://mlsanity.com/paper/2505.04732/) (2025)
- [FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.14227/) (2026)

## Abstract (arXiv)

In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM). TWOLAR introduces a new scoring strategy and a distillation process consisting in the creation of a novel and diverse training dataset. The dataset consists of 20K queries, each associated with a set of documents retrieved via four distinct retrieval methods to ensure diversity, and then reranked by exploiting the zero-shot reranking capabilities of an LLM. Our ablation studies demonstrate the contribution of each new component we introduced. Our experimental results show that TWOLAR significantly enhances the document reranking ability of the underlying model, matching and in some cases even outperforming state-of-the-art models with three orders of magnitude more parameters on the TREC-DL test sets and the zero-shot evaluation benchmark BEIR. To facilitate future work we release our data set, finetuned models, and code.