Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
Open accessAbstract
Retrieval Augmented Generation (RAG) has been a powerful tool for Large Language Models (LLMs) to efficiently process overly lengthy contexts.However, recent LLMs like Gemini-1.5 and GPT-4 show exceptional capabilities to understand long contexts directly.We conduct a comprehensive comparison between RAG and long-context (LC) LLMs, aiming to leverage the strengths of both.We benchmark RAG and LC across various public datasets using three latest LLMs.Results reveal that when resourced sufficiently, LC consistently outperforms RAG in terms of average performance.However, RAG's significantly lower cost remains a distinct advantage.Based on this observation, we propose SELF-ROUTE, a simple yet effective method that routes queries to RAG or LC based on model self-reflection.SELF-ROUTE significantly reduces the computation cost while maintaining a comparable performance to LC.Our findings provide a guideline for long-context applications of LLMs using RAG and LC.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
RAG primarily relies on surface-level lexical similarity between snippets and often fails to capture code segments with deeper semantic or functional dependencies-particularly when such relationships are implicit, abstracted, or span multiple components.
“While RAG effectively reduces context length, it primarily relies on surface-level lexical similarity between snippets. Consequently, it often fails to capture code segments with deeper semantic or functional dependencies-particularly when such relationships are implicit, abstracted, or span multiple components.”
From LongCodeZip: Compress Long Context for Code Language Models (2025) · cites this paper as [28]
Split into 2 atoms — 0 confirmed, 1 partially supported, 1 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredHybrid approaches achieve cost-effective performance through intelligent query routing.
“while hybrid approaches achieve cost-effective performance through intelligent query routing [17].”
From U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-in-a-Haystack (2026) · cites this paper as [17]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 42
- Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical re- port. arXiv preprint arXiv:2303.08774. · arXiv
- Chenxin An, Shansan Gong, Ming Zhong, Mukai Li, Jun Zhang, Lingpeng Kong, and Xipeng Qiu. 2023. L-eval: Instituting standardized evaluation for long context language models. arXiv preprint arXiv:2307.11088. · arXiv
- Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to re- trieve, generate, and critique through self-reflection. arXiv preprint arXiv:2310.11511. · arXiv
- Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, et al. 2023. Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508. · arXiv
- Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150. · arXiv
- Sebastian Borgeaud, Arthur Mensch, Jordan Hoff- mann, Trevor Cai, Eliza Rutherford, Katie Milli- can, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al. 2022. Improving language models by retrieving from tril- lions of tokens. In International conference on ma- chine learning, pages 2206-2240. PMLR.
- Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, and Jie Fu. 2024. Rq-rag: Learning to refine queries for retrieval augmented generation. arXiv preprint arXiv:2404.00610. · arXiv
- Lingjiao Chen, Matei Zaharia, and James Zou. 2023a. Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176. · arXiv
- Qinyuan Cheng, Xiaonan Li, Shimin Li, Qin Zhu, Zhangyue Yin, Yunfan Shao, Linyang Li, Tianxiang Sun, Hang Yan, and Xipeng Qiu. 2024. Unified active retrieval for retrieval augmented generation. arXiv preprint arXiv:2406.12534. · arXiv
- Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Co- han, Noah A Smith, and Matt Gardner. 2021. A dataset of information-seeking questions and an- swers anchored in research papers. arXiv preprint arXiv:2105.03011. · arXiv
- Mandy Guo, Joshua Ainslie, David C Uthus, Santi- ago Ontanon, Jianmo Ni, Yun-Hsuan Sung, and Yin- fei Yang. 2022. Longt5: Efficient text-to-text trans- former for long sequences. In Findings of the Associ- ation for Computational Linguistics: NAACL 2022, pages 724-736.
- Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pa- supat, and Mingwei Chang. 2020. Retrieval aug- mented language model pre-training. In Interna- tional conference on machine learning, pages 3929- 3938. PMLR.
- Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop qa dataset for comprehensive evaluation of reason- ing steps. arXiv preprint arXiv:2011.01060. · arXiv
- Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shan- tanu Acharya, Dima Rekesh, Fei Jia, and Boris Gins- burg. 2024. Ruler: What's the real context size of your long-context language models? arXiv preprint arXiv:2404.06654. · arXiv
- Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alexander Ratner, Ranjay Krishna, Chen-Yu Lee, and Tomas Pfister. 2023. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301. · arXiv
- Gautier Izacard, Mathilde Caron, Lucas Hosseini, Se- bastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense in- formation retrieval with contrastive learning. arXiv preprint arXiv:2112.09118. · arXiv
- Gautier Izacard and Edouard Grave. 2020. Lever- aging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282. · arXiv
- Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2024. Adaptive-rag: Learning to adapt retrieval-augmented large lan- guage models through question complexity. In Pro- ceedings of the 2024 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol- ume 1: Long Papers), pages 7029-7043.
- Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression. arXiv preprint arXiv:2310.06839. · arXiv
- Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172. · arXiv
- Tomáš Kočiskỳ, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gábor Melis, and Edward Grefenstette. 2018. The narrativeqa reading comprehension challenge. Transactions of the Asso- ciation for Computational Linguistics, 6:317-328.
- Yuri Kuratov, Aydar Bulatov, Petr Anokhin, Dmitry Sorokin, Artyom Sorokin, and Mikhail Burtsev. 2024. In search of needles in a 10m haystack: Recur- rent memory finds what llms miss. arXiv preprint arXiv:2402.10790. · arXiv
- Xiaonan Li, Changtai Zhu, Linyang Li, Zhangyue Yin, Tianxiang Sun, and Xipeng Qiu. 2023. Lla- trieval: Llm-verified retrieval for verifiable genera- tion. arXiv preprint arXiv:2311.07838. · arXiv
- Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to train your dragon: Diverse augmentation towards generalizable dense retrieval. arXiv preprint arXiv:2302.07452. · arXiv
- Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paran- jape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts. Transactions of the Asso- ciation for Computational Linguistics, 12:157-173.
- Yuanhua Lv and ChengXiang Zhai. 2009. Adaptive relevance feedback in information retrieval. In Pro- ceedings of the 18th ACM conference on Informa- tion and knowledge management, pages 255-264.
- Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting for retrieval- augmented large language models. arXiv preprint arXiv:2305.14283. · arXiv
- Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conver- sational memory of llm agents. arXiv preprint arXiv:2402.17753. OpenAI. 2023. Gpt-3.5-turbo. https://platform. openai.com/docs/models/gpt-3-5-turbo. · arXiv
- Machel Reid, Nikolay Savinov, Denis Teplyashin, Dmitry Lepikhin, Timothy Lillicrap, Jean-baptiste Alayrac, Radu Soricut, Angeliki Lazaridou, Orhan Firat, Julian Schrittwieser, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530. · arXiv
- Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, et al. 2022. Scrolls: Stan- dardized comparison over long language sequences. arXiv preprint arXiv:2201.03533. · arXiv
- Weijia Shi, Sewon Min, Michihiro Yasunaga, Min- joon Seo, Rich James, Mike Lewis, Luke Zettle- moyer, and Wen-tau Yih. 2023. Replug: Retrieval- augmented black-box language models. arXiv preprint arXiv:2301.12652. · arXiv
- Mingyang Song, Mao Zheng, and Xuan Luo. 2024. Counting-stars: A simple, efficient, and reasonable strategy for evaluating long-context large language models. arXiv preprint arXiv:2403.11802. · arXiv
- Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Mul- tihop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539-554.
- Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023. Self-knowledge guided retrieval augmentation for large language models. In Findings of the Associ- ation for Computational Linguistics: EMNLP 2023, pages 10303-10315.
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824- 24837.
- Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subra- manian, Evelina Bakhturina, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Retrieval meets long context large language models. arXiv preprint arXiv:2310.03025. · arXiv
- Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, and Zhen-Hua Ling. 2024. Corrective retrieval augmented gener- ation. arXiv preprint arXiv:2401.15884. · arXiv
- Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Ben- gio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answer- ing. arXiv preprint arXiv:1809.09600. · arXiv
- Tao Yuan, Xuefei Ning, Dong Zhou, Zhijie Yang, Shiyao Li, Minghui Zhuang, Zheyue Tan, Zhuyu Yao, Dahua Lin, Boxun Li, et al. 2024. Lv-eval: A balanced long-context benchmark with 5 length lev- els up to 256k. arXiv preprint arXiv:2402.05136. · arXiv
- Chengxiang Zhai and John Lafferty. 2001. Model- based feedback in the language modeling approach to information retrieval. In Proceedings of the tenth international conference on Information and knowl- edge management, pages 403-410.
- Xinrong Zhang, Yingfa Chen, Shengding Hu, Zi- hang Xu, Junhao Chen, Moo Khai Hao, Xu Han, Zhen Leng Thai, Shuo Wang, Zhiyuan Liu, et al. 2024. Infinity bench: Extending long context evaluation beyond 100k tokens. arXiv preprint arXiv:2402.13718. · arXiv
- Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, et al. 2021. Qmsum: A new benchmark for query-based multi- domain meeting summarization. arXiv preprint arXiv:2104.05938. · arXiv
Cited by
Sorted by citations
Loumachi, F. Y., Ghanem, M. C., & Ferrag, M. A. (2025) · Computers · doi:10.3390/computers14020067 · Cited by 40 · see citing works
Genovese, A., Prabha, S., Borna, S., Gomez-Cabello, C. A., Haider, S. A., Trabilsy, M., Tao, C., Aziz, K. T., Murray, P. M., & Forte, A. J. (2025) · Aesthetic Surgery Journal · doi:10.1093/asj/sjaf038 · Cited by 24 · see citing works
Ke, Y. H., Yang Ong, B. S., Jin, L., Sim, J. X. L., Chan, C. H., Soh, C. R., Wong, D. J. N., Liu, N., Sng, B. L., Ting, D. S. W., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01858-x · Cited by 19 · see citing works
Djeffal, C. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732118 · Cited by 10 · see citing works
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
Ray, S., Pan, R., Gu, Z., Du, K., Feng, S., Ananthanarayanan, G., Netravali, R., & Jiang, J. (2025) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3731569.3764855 · Cited by 17 · see citing works
Imran, M., & Lee, Y. (2026) · IEEE Access · doi:10.1109/access.2026.3656368 · Cited by 10 · see citing works
Kolhatin, A. O. (2025) · CEUR Workshop Proceedings, Vol-4060: Proceedings of the 8th International Workshop on Augmented Reality in Education (AREdu 2025) · doi:10.55056/ceur-ws.org/vol-4060/paper05.pdf · Cited by 6 · see citing works
U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack
Gao, Y., Xiong, Y., Wu, W., Huang, Z., Li, B., & Wang, H. (2025) · arXiv · doi:10.48550/arxiv.2503.00353 · Cited by 6 · see citing works
U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-in-a-Haystack
Gao, Y., Xiong, Y., Wu, W., Li, B., Zhong, Y., & Wang, H. (2026) · ACM Transactions on Information Systems · doi:10.1145/3786609 · Cited by 6 · see citing works
Kim, S. H., Schramm, S., Schmitzer, L., Serguen, K., Ziegelmayer, S., Busch, F., Komenda, A., Makowski, M. R., Adams, L. C., Bressem, K. K., et al. (2025) · European Radiology · doi:10.1007/s00330-025-11989-0 · Cited by 5 · see citing works
LongCodeZip: Compress Long Context for Code Language Models
Shi, Y., Qian, Y., Zhang, H., Shen, B., & Gu, X. (2025) · 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00020 · Cited by 7 · see citing works
Tyndall, E., Gayheart, C., Some, A., Genz, J., Wagner, T. J., & Langhals, B. T. (2025) · Data & Policy · doi:10.1017/dap.2025.10024 · Cited by 4 · see citing works
Meta-X design: from tools to partners in human–machine co–creation for industry 5.0
Yu, C., Yan, T., & Chen, Y. (2025) · Journal of Engineering Design · doi:10.1080/09544828.2025.2571005 · Cited by 4 · see citing works
Haviana, S. F. C., Riyadi, M. A., & Kusumaningrum, R. (2025) · Proceeding of the Electrical Engineering Computer Science and Informatics · doi:10.1109/eecsi67060.2025.11290624 · Cited by 4 · see citing works
Akçalı, Z., Çubuk, H. S., Oğuz, A., Koçak, M., Farzaliyeva, A., Guven, F., Ramazanoğlu, M. N., Hasdemir, E., Altundağ, Ö., & Ağıldere, A. M. (2025) · Bioengineering · doi:10.3390/bioengineering12020168 · Cited by 3 · see citing works
How Experience Moderates the Impact of Generative AI Ideas on the Research ProcessPreprint
Doshi, A. R., Chai, S., & Troebinger, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5013086 · Cited by 3 · see citing works
L3X: Long Object List Extraction from Long Documents
Singhania, S., Razniewski, S., & Weikum, G. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761460 · Cited by 2 · see citing works
Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA
Zhu, X., Li, H., Zhang, Y., & Chen, L. (2026) · Proceedings of the ACM on Management of Data · doi:10.1145/3802111 · Cited by 2 · see citing works
Adaptation of Embedding Models to Financial Filings Via LLM Distillation
Brenner, E., Seyler, D., Hegde, M., Simion, A., Dasgupta, K., & Xiang, B. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402604 · Cited by 1 · see citing works
ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs
Pan, R., Mao, B., Ma, T., & Ling, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462552 · Cited by 1 · see citing works
Confidence-Conflict Routing Between Parametric Memory, RAG, and Long-Context LLMs
Fang, R., Zhou, J., Zhu, Z., Hu, R., & Zheng, Y. (2026) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis70504.2026.11633419 · Cited by 1 · see citing works
Lu, Y., Huang, Z., & Cheng, T. (2026) · Information Development · doi:10.1177/02666669261466636 · Cited by 1 · see citing works
Future Trends and Challenges in Generative AI for Photonic Sensing
Chaurasia, A., Banik, O., Kumar, S., & Banoth, E. (2025) · Progress in optical science and photonics · doi:10.1007/978-981-95-1561-5_10
Sikos, L. F. (2025) · SpringerBriefs in cybersecurity · doi:10.1007/978-3-032-05250-6_1 · Cited by 1 · see citing works
Retrieval-Augmented Generation Chatbot: An Application to Support Candidates in the Recruitment
Dung, N. V., & Thanh, P. Q. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-13806-4_21
Dhanya, K. R., Vijayan, N., & Ranjani, R. (2025) · IEEE Silchar Subsection Conference (SILCON) · doi:10.1109/silcon67893.2025.11326921
Explainable Knowledge Access: Recursive and Rerank-Based RAG for Interpretable QA
Cosseddu, M., Giuliani, A., Manca, M. M., Pilloni, M., Podda, A. S., & Tiddia, S. G. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-15638-9_13
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k
Taguchi, C., Maekawa, S., & Bhutani, N. (2026) · Journal of Natural Language Processing · doi:10.5715/jnlp.33.382
Surk, E., Dalveren, G. G. M., & Derawi, M. O. (2026) · Applied Sciences · doi:10.3390/app16062801
Silva, K. N. N. C. D., Jayawickrama, D. S. K., Weerasingha, W. G. K. M., & Liyanage, D. L. C. P. (2026) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc68737.2026.11453918
Arora, A., Garg, S., Nandani, & Seeja, K. R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14186-6_12
From Answer to Origin: Page Number Grounding in Document-Level Question Answering
Shejuti, Z. T., Deb, D., & Dunkel, E. R. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00075
Token Cost Optimization in an LLM Agent for JSON-Based System Modeling from Dialogue History
Lavrentiev, S., & Dukhanov, A. V. (2026) · International Russian Smart Industry Conference (SmartIndustryCon) · doi:10.1109/smartindustrycon68821.2026.11493004
NextRAG: A Bilingual Retrieval-Augmented Generation Framework for Financial Question-Answering
Opin, S. A. I., Thakur, R. A., Raiyan, A. K., Kabir, M. R., & Rahman, S. M. A. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491522
A comparative study of RAG and HyDE RAG: Enhancing retrieval and generation performance
Naveen, D., Bag, S., Dsouza, J., Prashanth, R. J., & Siddalingappa, R. (2026) · AIP conference proceedings · doi:10.1063/5.0341463
The Emerging Role of Large Language Models in Threat Modelling: A Survey
Buseth, P., Amro, A., Kollarou, A., Takaronis, M., Lehkonen, R., & Shaikh, S. (2026) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi68585.2026.11539950
A BART-Enhanced Hybrid Framework for Multi-Document Summarization
Ihsan, U., Jhanjhi, N., Ashraf, H., Malik, J., & Sukmawan, D. (2026) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc69565.2026.11542559
Mishra, S. K., Singh, M., Saravanan, S., Kumar, T. R., Robert, P., & Sivakumar, S. (2026) · International Conference on Intelligent Computing and Automation for Sustainable Solutions (ICASS) · doi:10.1109/icass69550.2026.11547758
Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation
Song, Z., Fang, J., Li, K., Xia, T., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37667-1_12 · Cited by 2 · see citing works
Wilde, L. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-8424-5.ch004
Slany, E., Buchmann, S., Föhr, T. L., Amling, J., Frummet, A., Lang, M., & Scheele, S. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-30809-2_28
The Evolution of SEO in the Era of Generative AI: A Business Intelligence Perspective
Roumeliotis, K. I., Margaris, D., Spiliotopoulos, D., & Vassilakis, C. (2026) · Electronics · doi:10.3390/electronics15163541
CAGE: An Evaluation Framework for Cache-Augmented Generation Models
do Carmo, L. M., Brandão, W. C., & de Freitas, H. C. (2026) · Anais do Workshop em Desempenho de Sistemas Computacionais e de Comunicação (WPerformance) · doi:10.5753/wperformance.2026.23603
Nascimento, V. S. D. O., Tedardi, M. V., Rogério, G. D. S., Pinello, K. C., & Dagli, M. L. (2026) · Cancers · doi:10.3390/cancers18172728
ORCASK: A Multi-Agent Tool for Automated Network Configuration of Open Network Switches
HOSSAINI, M. H., Kassler, A., & Bhatt, K. (2026) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms69089.2026.11668126
Wang, X., & Lu, J. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1937335
Tao, L., Li, Z., Ji, Y., Liao, C.-T., Xiao, X., & Cao, X. (2026) · Symmetry · doi:10.3390/sym18091498
Self-citationSblendorio, E., Dentamaro, V., Maria, M. D., Tempesta, S., Barile, E., Napolitano, D., Tallini, M., Nigrelli, D., Cicolini, G., & Piredda, M. (2026) · JMIR Medical Informatics · doi:10.2196/90854
A Survey on Optimizing Retrieval Augmented Generation Applications
Naveen, R., Bag, S., Franklin, J., & Thontadari, C. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-1243-9_14
Needle in a Knowledge Graph: Generating Scalable Long-Context Benchmarks for KG Question Answering
Sturm, J., Ellinger, L., Luckow, A., & Groh, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-42224-8_4
- Authors
- Li, Z., Li, C., Zhang, M., Mei, Q., & Bendersky, M.
- Affiliations
- University of Michigan (US)
- Venue
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
- Published
- 2024
- Pages
- 881-893
- OpenAlex
- W4404783788
- Cited by
- 49
- References
- 0
- Citations by year
- 2026: 28 · 2025: 21
- FWCI
- 14.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- retrieval-augmented generation, long-context large language models, hybrid retrieval-augmented generation, query routing, computation cost reduction, long-context understanding, LLM benchmarking
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
