# PaRaDe: Passage Ranking using Demonstrations with Large Language Models

arXiv: https://arxiv.org/abs/2310.14408 · HTML: https://mlsanity.com/paper/2310.14408/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2023.

## Built on by (most cited first, 10 of 10)

- [In-context Learning with Retrieved Demonstrations for Language Models: A Survey](https://mlsanity.com/paper/2401.11624/) (2024)
- [Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking](https://mlsanity.com/paper/2506.09944/) (2025)
- [DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.07233/) (2025)
- [Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.03689/) (2026)
- [Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching](https://mlsanity.com/paper/2506.04579/) (2025)
- [RARe: Retrieval Augmented Retrieval with In-Context Examples](https://mlsanity.com/paper/2410.20088/) (2024)
- [GenSERP: Large Language Models for Whole Page Presentation](https://mlsanity.com/paper/2402.14301/) (2024)
- [Access Paths for Efficient Ordering with Large Language Models](https://mlsanity.com/paper/2509.00303/) (2025)
- [Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders](https://mlsanity.com/paper/2601.05588/) (2026)
- [Context-Picker: Dynamic context selection using multi-stage reinforcement learning](https://mlsanity.com/paper/2512.14465/) (2025)

## Abstract (arXiv)

Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method, such as BM25, are rated and reordered to improve relevance. In this work, we improve LLM-based re-ranking by algorithmically selecting few-shot demonstrations to include in the prompt. Our analysis investigates the conditions where demonstrations are most helpful, and shows that adding even one demonstration is significantly beneficial. We propose a novel demonstration selection strategy based on difficulty rather than the commonly used semantic similarity. Furthermore, we find that demonstrations helpful for ranking are also effective at question generation. We hope our work will spur more principled research into question generation and passage ranking.