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

• URL: http://arxiv.org/abs/2604.27599v1
• Date: Thu, 30 Apr 2026 08:49:44 GMT
• Title: One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
• Abstract summary: Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candidates are presented.<n>This creates a mismatch between the set-based nature of recommendation and the sequence-based computation of decoder-only LLMs.<n>We propose InvariRank, a permutation-invariant listwise reranking framework that addresses this dependence at the architectural level.
• Score: 2.5827686695037335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking [2.5827686695037335]
  We study how position bias affects the ranking process induced by LLM-based rerankers.<n>We introduce an evaluation framework measuring pairwise preference instability, global preference inconsistency, and listwise output consistency.
  arXiv  Detail & Related papers  (2026-08-04T04:04:12Z)
• Structure-aware Relative Policy Optimization for Ranking [35.05747484313467]
  We propose SRPO, a textbfStructure-aware textbfRelative textbfPolicy textbfOptimization framework for listwise ranking.<n>It measures the discrepancy between sampled permutations using a top-weighted Kendall-tau distance and normalizes their pairwise reward differences by the corresponding distances.<n> Experimental results across two ranking scenarios demonstrate that explicitly modeling permutation-level differences improves the effectiveness and stability of listwise ranking.
  arXiv  Detail & Related papers  (2026-07-28T04:13:47Z)
• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning [70.6126069527741]
  ConvRec-R1 is a two-stage framework for end-to-end training of conversational recommender systems.<n>In Stage 1, we construct a behavioral-cloning dataset with a Remap-Reflect-Adjust pipeline.<n>In Stage 2, we propose Rank-GRPO, a principled extension of group relative policy optimization.
  arXiv  Detail & Related papers  (2025-10-23T02:56:00Z)
• Self-Calibrated Listwise Reranking with Large Language Models [137.6557607279876]
  Large language models (LLMs) have been employed in reranking tasks through a sequence-to-sequence approach. This reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. We propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking.
  arXiv  Detail & Related papers  (2024-11-07T10:31:31Z)
• Make Large Language Model a Better Ranker [20.532118635672763]
  This paper introduces the large language model framework with Aligned Listwise Ranking Objectives (ALRO) ALRO is designed to bridge the gap between the capabilities of LLMs and nuanced requirements of ranking tasks. Our evaluative studies reveal that ALRO outperforms both existing embedding-based recommendation methods and LLM-based recommendation baselines.
  arXiv  Detail & Related papers  (2024-03-28T07:22:16Z)
• Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models [63.714662435555674]
  Large language models (LLMs) exhibit positional bias in how they use context. We propose permutation self-consistency, a form of self-consistency over ranking list outputs of black-box LLMs. Our approach improves scores from conventional inference by up to 7-18% for GPT-3.5 and 8-16% for LLaMA v2 (70B)
  arXiv  Detail & Related papers  (2023-10-11T17:59:02Z)
• Replace Scoring with Arrangement: A Contextual Set-to-Arrangement Framework for Learning-to-Rank [40.81502990315285]
  Learning-to-rank is a core technique in the top-N recommendation task, where an ideal ranker would be a mapping from an item set to an arrangement. Most existing solutions fall in the paradigm of probabilistic ranking principle (PRP), i.e., first score each item in the candidate set and then perform a sort operation to generate the top ranking list. We propose Set-To-Arrangement Ranking (STARank), a new framework directly generates the permutations of the candidate items without the need for individually scoring and sort operations.
  arXiv  Detail & Related papers  (2023-08-05T12:22:26Z)
• PiRank: Learning To Rank via Differentiable Sorting [85.28916333414145]
  We propose PiRank, a new class of differentiable surrogates for ranking. We show that PiRank exactly recovers the desired metrics in the limit of zero temperature.
  arXiv  Detail & Related papers  (2020-12-12T05:07:36Z)
• SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback [50.13745601531148]
  We propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons. We also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to $sqrtM/N$.
  arXiv  Detail & Related papers  (2020-02-23T06:40:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.