Lune

ACL Findings2025

Exploring Knowledge Filtering for Retrieval-Augmented Discriminative Tasks

Minjie Qiang, Zhongqing Wang, Xiaoyi Bao, Haoyuan Ma, Shoushan Li, Guodong Zhou

Abstract

Retrieval-augmented methods have achieved remarkable advancements in alleviating the hallucination of large language models. Nevertheless, the introduction of external knowledge does not always lead to the expected improvement in model performance, as irrelevant or harmful information present in the retrieved knowledge can compromise the prediction process. To address these challenges, we propose a novel framework aimed at improving model performance by incorporating knowledge filtering and prediction fusion mechanisms. In particular, our approach first employs a perplexitybased annotation method to collect training data. Then, we design four distinct strategies to filter out harmful retrieved knowledge. Finally, we integrate the filtered knowledge to generate the final result via batch-wise predictions. We conduct extensive experiments across multiple discriminative task datasets to evaluate the proposed framework. The results demonstrate that our framework can significantly enhance the performance of models on discriminative tasks.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation cites Large Language Models Can Be Easily Distracted by Irrelevant Context
  • Making Retrieval-Augmented Language Models Robust to Irrelevant Context cites Large Language Models Can Be Easily Distracted by Irrelevant Context
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk AssessmentYiran Qiao, Xiang Ao, Jing Chen, Yang Liu et al.SIGIR 2026 · 2 citations

Builds on21

  1. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
  2. Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales et al.ICML 2023 · 970 citations
  3. Large Language Models Struggle to Learn Long-Tail KnowledgeNikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace et al.ICML 2023 · 623 citations
  4. Making Retrieval-Augmented Language Models Robust to Irrelevant ContextOri Yoran, Tomer Wolfson, Ori Ram, Jonathan BerantICLR 2024 · 361 citations
  5. RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective AugmentationFangyuan Xu, Weijia Shi, Eunsol ChoiICLR 2024 · 260 citations

Related papers

  1. BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge FilteringHaoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian et al.EMNLP 2024 · 9 citations
  2. Empowering GraphRAG with Knowledge Filtering and IntegrationKai Guo, Harry Shomer, Shenglai Zeng, Haoyu Han et al.EMNLP 2025 · 2 citations
  3. RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-FeedbackYanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu et al.ACL Findings 2024 · 35 citations
  4. Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement LearningYuqin Dai, Shuo Yang, Guoqing Wang, Yong Deng et al.AAAI 2026 · 5 citations
  5. Expert-guided Clinical Text Augmentation via Query-Based Model CollaborationDongkyu Cho, Miao Zhang, Gregory Lyng, Rumi ChunaraICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines