Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2601.02993v3
• Date: Fri, 09 Jan 2026 14:55:53 GMT
• Title: Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
• Abstract summary: Retrieval-Augmented Generation has become a key paradigm for reducing factual hallucinations in large language models.<n>We propose Stable-RAG, which exploits permutation sensitivity estimation to mitigate permutation-induced hallucinations.
• Score: 24.598044386822508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in large language models (LLMs), yet little is known about how the order of retrieved documents affects model behavior. We empirically show that under Top-5 retrieval with the gold document included, LLM answers vary substantially across permutations of the retrieved set, even when the gold document is fixed in the first position. This reveals a previously underexplored sensitivity to retrieval permutations. Although robust RAG methods primarily focus on enhancing LLM robustness to low-quality retrieval and mitigating positional bias to distribute attention fairly over long contexts, neither approach directly addresses permutation sensitivity. In this paper, we propose Stable-RAG, which exploits permutation sensitivity estimation to mitigate permutation-induced hallucinations. Stable-RAG runs the generator under multiple retrieval orders, clusters hidden states, and decodes from a cluster-center representation that captures the dominant reasoning pattern. It then uses these reasoning results to align hallucinated outputs toward the correct answer, encouraging the model to produce consistent and accurate predictions across document permutations. Experiments on three QA datasets show that Stable-RAG significantly improves answer accuracy, reasoning consistency and robust generalization across datasets, retrievers, and input lengths compared with baselines.

Related papers

• WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval [11.681276883454288]
  We propose Wildcard Inference with Dynamic Expansion (WIDE) to overcome the problem of forced hallucination in cross-modal retrieval.<n>During the decoding generation phase, Asymmetry-aware Wildcard Decoding (AWD) detects semantic blind spots and emits wildcards instead of forced deterministic identifiers.<n>Blind-Spot Re-ranking (BSR) evaluates the expanded candidate pool using a hybrid scoring mechanism that combines discrete generation confidence with continuous semantic similarity.
  arXiv  Detail & Related papers  (2026-09-03T08:55:05Z)
• Latent Abstraction for Retrieval-Augmented Generation [4.6096940605642915]
  Existing systems rely on generating natural language queries at each hop.<n>We propose textbfLAnR (Latent Abstraction for RAG), a unified framework in which a single LLM jointly performs encoding, retrieval, and generation entirely within its own latent space.
  arXiv  Detail & Related papers  (2026-04-20T06:26:13Z)
• Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models [22.663638862390467]
  We propose Order-Aware Knowledge Hypergraph RAG, which treats order as a first-class structural property.<n> OKH-RAG represents knowledge as higher-order interactions within a hypergraph augmented with precedence structure.<n>We evaluate OKH-RAG on order-sensitive question answering and explanation tasks, including tropical cyclone and port operation scenarios.
  arXiv  Detail & Related papers  (2026-04-14T01:31:35Z)
• Gaussian Match-and-Copy: A Minimalist Benchmark for Studying Transformer Induction [44.83333974000826]
  We introduce a minimalist benchmark that isolates long-range retrieval through pure second-order correlation signals.<n> Numerical investigations show that this task retains key qualitative aspects of how Transformers develop match-and-copy circuits.<n>We prove this max-margin alignment for GD trajectories that reach vanishing empirical loss under explicit technical conditions.
  arXiv  Detail & Related papers  (2026-02-07T14:18:11Z)
• Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation [64.09110141948693]
  Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise.<n>We propose BAR-RAG, which reframes the reranker as a boundary-aware evidence selector that targets the generator's Goldilocks Zone.<n>Bar-RAG consistently improves end-to-end performance under noisy retrieval.
  arXiv  Detail & Related papers  (2026-02-03T16:08:23Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers [2.007262412327553]
  CoopRAG is a novel RAG framework for the question answering task in which a retriever and an LLM work cooperatively with each other.<n>Our experiments demonstrate that CoopRAG consistently outperforms state-of-the-art QA methods on three multi-hop QA datasets as well as a simple QA dataset.
  arXiv  Detail & Related papers  (2025-12-11T08:35:17Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation [24.108631023133704]
  IterKey is an iterative keyword generation framework that enhances RAG via sparse retrieval.<n>It achieves 5% to 20% accuracy improvements over BM25-based RAG and simple baselines.
  arXiv  Detail & Related papers  (2025-05-13T11:25:15Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation [47.091086803980765]
  We propose consistency regularization with augmentation and distillation.<n>We propose CORD, balancing COnsistency and Rank Distillation.<n> Empirical results show this balance enables CORD to outperform consistently in diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-12-19T07:01:25Z)
• Corrective Retrieval Augmented Generation [36.04062963574603]
  Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
  arXiv  Detail & Related papers  (2024-01-29T04:36:39Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Noise-Robust Dense Retrieval via Contrastive Alignment Post Training [89.29256833403167]
  Contrastive Alignment POst Training (CAPOT) is a highly efficient finetuning method that improves model robustness without requiring index regeneration. CAPOT enables robust retrieval by freezing the document encoder while the query encoder learns to align noisy queries with their unaltered root. We evaluate CAPOT noisy variants of MSMARCO, Natural Questions, and Trivia QA passage retrieval, finding CAPOT has a similar impact as data augmentation with none of its overhead.
  arXiv  Detail & Related papers  (2023-04-06T22:16:53Z)

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.