Passage Attribution for Evidence-Grounded Retrieval-Augmented Generation under Noisy Retrieval
Keywords:
Retrieval-Augmented Generation, Passage Attribution, Noisy Retrieval, Hallucination Mitigation, Natural Language ProcessingAbstract
Retrieval-Augmented Generation has emerged as a dominant paradigm for mitigating hallucinations in large language models by grounding generated responses in external knowledge sources. However, the efficacy of these systems is fundamentally bottlenecked by the quality of the retrieved documents. In real-world applications, retrieval components frequently return noisy, irrelevant, or contradictory passages, which can severely degrade the factual accuracy and coherence of the generated output. This paper presents a comprehensive investigation into passage attribution mechanisms designed to fortify evidence-grounded generation under conditions of high retrieval noise. We introduce a novel architectural framework that dynamically evaluates and assigns attribution scores to retrieved passages before generation, enabling the language model to selectively attend to highly relevant evidence while discarding spurious noise. Through extensive theoretical analysis and empirical evaluation across multiple domain-specific datasets, we demonstrate that explicit passage attribution not only improves response factuality but also enhances the interpretability of the generation process. Our findings indicate that integrating dynamic thresholding and robust training objectives significantly increases the resilience of generative models against adversarial or noisy retrieval outcomes. The proposed methodology establishes a new benchmark for developing trustworthy, verifiable, and noise-resilient natural language processing systems.
References
1. Gao, Z., Qu, Y., & Han, Y. (2025). Cross-Lingual Sponsored Search via Dual-Encoder and Graph Neural Networks for Context-Aware Query Translation in Advertising Platforms. arXiv preprint arXiv:2510.22957.
2. Zhu, R., Jiang, X., Wu, J., Ma, Z., Song, J., Bai, F., ... & He, C. (2025, April). GRAIT: gradient-driven refusal-aware instruction tuning for effective hallucination mitigation. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 4006-4021).
3. Tang, J., Yang, Y., Yu, J., Wang, Z. X., Liang, H., Yao, L., & Yin, J. (2025, November). Unco: Uncertainty-driven collaborative framework of large and small models for grounded multimodal ner. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 7644-7662).
4. Mao, C., Shuang, K., Guo, J., Qian, B., Yang, Y., & Li, H. (2026). Cognition-aligned frequency filtering for sentence embeddings. Information Processing & Management, 63(2), 104415.
5. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT.
6. Han, C., Zheng, W., & Tang, X. (2025, November). Debate-to-detect: Reformulating misinformation detection as a real-world debate with large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 15125-15140).
7. Shuang, K., Zhou, J., Wang, Q., Qian, B., Wei, Y., & Guo, J. (2025). Utilizing contextual summarizing and reasoning for enhancing document-level event argument extraction. Expert Systems with Applications, 287, 128075.
8. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.
9. Wei, W. D., Fang, H. B., Liu, Y. D., Shi, J. X., Kwok, J., & Li, Y. F. (2026). Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm. arXiv preprint arXiv:2605.01255.
10. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2026). UAV-RHS-enabled full-duplex ISAC covert system: Robust beamforming and trajectory optimization. IEEE Transactions on Communications.
11. Tang, J., Yuan, X., Liu, J., Yu, J., Dong, X., Chen, L., ... & Yin, J. (2026). SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition. arXiv preprint arXiv:2604.20146.
12. Xu, X., Tu, W., & Yang, Y. (2024). Adaptive selection of local and non-local attention mechanisms for speech enhancement.Neural Networks,174, 106236.
13. Sang, Y. (2025, August). Robustness of fine-tuned llms under noisy retrieval inputs. In 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) (pp. 417-420). IEEE.
14. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.
15. Sang, Y. (2025, October). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1177-1180). IEEE.
16. Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In Proceedings of ICLR.
17. Zhu, R., Ma, Z., Wu, J., Gao, J., Wang, J., Lin, D., & He, C. (2025, April). Utilize the flow before stepping into the same river twice: Certainty represented knowledge flow for refusal-aware instruction tuning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 26157-26165).
18. Yao, Y., Xiao, W., Miao, P., Chen, G., Yang, H., Chae, C. B., & Wong, K. K. (2025). UAV-relay-aided secure maritime networks coexisting with satellite networks: robust beamforming and trajectory optimization. IEEE Transactions on Wireless Communications.
19. Yao, Y., Zhang, J., Miao, P., Zhang, L., Chen, G., Shu, F., & Wong, K. K. (2025). Hybrid RIS-enhanced ISAC secure systems: Joint optimization in the presence of an extended target. IEEE Transactions on Communications.
20. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
21. Wang, S. (2025, May). W-PCA based gradient-free proxy for efficient search of lightweight language models. In International Conference on Learning Representations (Vol. 2025, pp. 42419-42440).
22. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs develop languages: Symbolic communication for efficient multi-agent reasoning.arXiv preprint arXiv:2606.29354.
23. Li, Y., Yang, Z., Huang, Y., Liu, X., & Qi, G. (2026, March). C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 38, pp. 31834-31842).
24. Li, K., Shuang, K., & Guo, J. (2026). Bring order to the jumbled input: Layered attention for Large Language Model based Event Argument Extraction. Engineering Applications of Artificial Intelligence, 165, 113399.
25. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
26. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
27. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., et al. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
28. Xiao, Q., & Zhou, K. (2026). MACD: Model-Aware Contrastive Decoding via Counterfactual Data. arXiv preprint arXiv:2602.01740.
29. Xie, Z., Liao, R., Wang, Z., Chen, C., Hua, X. S., & Luo, X. (2026, July). GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 10281-10293).
30. Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.
31. Tang, J., Wang, Z., Gong, Z., Yu, J., Zhu, X., & Yin, J. (2025, April). Multi-grained query-guided set prediction network for grounded multimodal named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 25246-25254).
32. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
33. Yang Y, Yang X, Jiang Y, et al. GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems[J]. arXiv preprint arXiv:2602.15776, 2026.
34. Xu, X., Zhang, Y., Li, J., Yang, Y., Luo, Y., & Tu, W. (2025, May). FIRING-Net: A filtered feature recycling network for speech enhancement. In International Conference on Learning Representations (Vol. 2025, pp. 33204-33230).
35. Li, Y., Bai, X., Liu, S., & Zhang, L. (2026). RepBench: Compiling benchmarks into capability representations for large language models. arXiv. https://arxiv.org/abs/2607.28008
36. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement generative adversarial network. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(pp. 7308-7311). IEEE.
37. Liu, H., Ding, L., & Henao, R. (2026, July). Learning to Control Summaries with Score Ranking. In Findings of the Association for Computational Linguistics: ACL 2026(pp. 35336-35359).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Software Engineering and Artificial Intelligence Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
