mlsanityData to 14 Oct 2026

Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention

arXiv 2609.35794 ↗First posted 17 Sep 2026cs.CL cs.LGcited by 0

On the map: Retrieval-augmented generation → Generation and context integration also fits: RAG robustness and adaptive retrieval

Abstract (arXiv)

Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single step, resulting in limited abstention performance and high computational costs. We instead decompose retrieval failures into two distinct states: (i) the unanswerable state, where the required evidence is absent, and (ii) the distracted state, where relevant evidence is mixed with conflicting, negated, or adversarial information. Based on this decomposition, we introduce a lightweight module (Sieve) that screens retrieved document sets for distracting evidence before invoking a costly LLM (Sage) for grounded generation and abstention. Evaluated across both general and high-stakes expert domains, our Sieve and Sage framework preemptively detects distracting noise, improving system accuracy by up to 69.4 percentage points and Macro-F1 by 55.2 percentage points compared to one-stage baselines. Furthermore, it achieves up to a 1.99x speedup, establishing a highly efficient and reliable abstention pipeline for RALM with abstention.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 22 of its 36 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

22 of 36 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning8 Aug
  2. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models15 Nov
  3. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Context2 Oct
  4. 2023In-Context Retrieval-Augmented Language Models31 Jan
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan

Other references · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2020Longformer: The Long-Document Transformercited by 3,413
  4. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  5. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  6. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  7. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  8. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 159
  9. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 151
  10. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89
  11. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 72
  12. 2014Question Answering with Subgraph Embeddingscited by 58
5 more
  1. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noisecited by 54
  2. 2024Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approachescited by 52
  3. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 41
  4. 2025Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAGcited by 14
  5. 2025MASH: Modeling Abstention via Selective Help-Seekingcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding
  2. 2025Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
  3. 2026UNREAL: Unifying Retrieval and Long-Context with a Single Model
  4. 2024FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inference
  5. 2026Tackling the Inherent Difficulty of Noise Filtering in RAG
  6. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing
  7. 2025Do Retrieval-Augmented Language Models Adapt to Varying User Needs?
  8. 2026Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks