# One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation

arXiv: https://arxiv.org/abs/2604.27599 · HTML: https://mlsanity.com/paper/2604.27599/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models](https://mlsanity.com/paper/2310.09497/) (2023)
- [LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations](https://mlsanity.com/paper/2406.12433/) (2024)
- [RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation](https://mlsanity.com/paper/2312.16018/) (2023)
- [Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models](https://mlsanity.com/paper/2310.07712/) (2023)
- [Evaluating Position Bias in Large Language Model Recommendations](https://mlsanity.com/paper/2508.02020/) (2025)
- [Large Language Models are Not Stable Recommender Systems](https://mlsanity.com/paper/2312.15746/) (2023)
- [Do RAG Systems Really Suffer From Positional Bias?](https://mlsanity.com/paper/2505.15561/) (2025)
- [Make Large Language Model a Better Ranker](https://mlsanity.com/paper/2403.19181/) (2024)
- [Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs](https://mlsanity.com/paper/2404.01430/) (2024)

## Built on by (most cited first, 5 of 5)

- [Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders](https://mlsanity.com/paper/2607.24869/) (2026)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)
- [Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation](https://mlsanity.com/paper/2609.00086/) (2026)
- [Jev Matches 7B Language Models for Speech-Neuroprosthesis Rescoring](https://mlsanity.com/paper/2609.33538/) (2026)
- [Consider, Then Choose: Order-Invariant Decisions in System One Models](https://mlsanity.com/paper/2610.18233/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candidates are presented. This creates a mismatch between the set-based nature of recommendation and the sequence-based computation of decoder-only LLMs, where permuting an otherwise identical candidate set can change item scores and final rankings. Such order sensitivity makes LLM-based rerankers difficult to rely on, since rankings may reflect prompt serialization rather than user preference. We propose InvariRank, a permutation-invariant listwise reranking framework that addresses this dependence at the architectural level. InvariRank blocks cross-candidate attention with a structured attention mask and negates position-induced scoring changes through shared positional framing under Rotary Positional Embeddings (RoPE). Combined with a listwise learning-to-rank objective, the model scores all candidates in a single forward pass, avoiding permutation-based invariance training objectives that require multiple permutations of a candidate set. Experiments on recommendation benchmarks show that InvariRank maintains competitive ranking effectiveness while producing stable rankings across candidate permutations. The results suggest that architectural invariance is a practical route to reliable and efficient LLM-based recommendation reranking. The source code is at https://github.com/ejbito/InvariRank.