[1]

OpenAI, Achiam J, Adler S, Agarwal S, Ahmad L, et al. 2023. GPT-4 technical report. arXiv Preprint:2303.08774

doi: 10.48550/arXiv.2303.08774
[2]

Grattafiori A, Dubey A, Jauhri A, Pandey A, Kadian A, et al. 2024. The llama 3 herd of models. arXiv Preprint:2407.21783

doi: 10.48550/arXiv.2407.21783
[3]

Georgiev P, Lei VI, Burnell R, Bai L, Gulati A, et al. 2024. Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv Preprint:2403.05530

doi: 10.48550/arXiv.2403.05530
[4]

Lee T, Yoon C, Jang K, Lee D, Song M, et al. 2025. ETHIC: evaluating large language models on long-context tasks with high information coverage. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). April 2025. Albuquerque, New Mexico. USA: Association for Computational Linguistics. pp. 5497–5512 doi: 10.18653/v1/2025.naacl-long.283
[5]

Wang X, Liu J, Xiao Y, Ning J, Liu L, et al. 2025. THE-Tree: can tracing historical evolution enhance scientific verification and reasoning? arXiv Preprint:2506.21763

doi: 10.48550/arXiv.2506.21763
[6]

Schryen G, Marrone M, Yang J. 2025. Exploring the scope of generative AI in literature review development. Electronic Markets 35(1):13

doi: 10.1007/s12525-025-00754-2
[7]

Lála J, O'Donoghue O, Shtedritski A, Cox S, Rodriques SG, et al. 2023. PaperQA: retrieval-augmented generative agent for scientific research. arXiv Preprint:2312.07559

doi: 10.48550/ARXIV.2312.07559
[8]

Asai A, He J, Shao R, Shi W, Singh A, et al. 2024. OpenScholar: synthesizing scientific literature with retrieval-augmented lms. arXiv Preprint:2411.14199

doi: 10.48550/ARXIV.2411.14199
[9]

Auer S, Barone DAC, Bartz C, Cortes EG, Jaradeh MY, et al. 2023. The SciQA scientific question answering benchmark for scholarly knowledge. Scientific Reports 13(1):7240

doi: 10.1038/s41598-023-33607-z
[10]

Wang X, Hu Z, Lu P, Zhu Y, Zhang J, et al. 2024. SciBench: evaluating college-level scientific problem-solving abilities of large language models. arXiv Preprint:2307.10635

doi: 10.48550/arXiv.2307.10635
[11]

Vladika J, Matthes F. 2024. Improving health question answering with reliable and time-aware evidence retrieval. Findings of the Association for Computational Linguistics: NAACL 2024. June 2024. Mexico City, Mexico. USA: Association for Computational Linguistics. pp. 4752–4763 doi: 10.18653/v1/2024.findings-naacl.295
[12]

Fang J, Meng Z, MacDonald C. 2024. TRACE the evidence: constructing knowledge-grounded reasoning chains for retrieval-augmented generation. Findings of the Association for Computational Linguistics: EMNLP 2024. November 2024. Miami, Florida, USA. USA: Association for Computational Linguistics. pp. 8472–8494 doi: 10.18653/v1/2024.findings-emnlp.496
[13]

Lan Y, He G, Jiang J, Jiang J, Zhao WX, et al. 2021. A survey on complex knowledge base question answering: methods, challenges and solutions. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Survey Track. 19–26 August 2021. Montreal, Canada. USA: International Joint Conferences on Artificial Intelligence Organizationpp. pp. 4483–4491 doi: 10.24963/ijcai.2021/611
[14]

Zhang N, Gui T, Nan G. 2022. Efficient and robust knowledge graph construction. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Tutorial Abstracts. November 2022. Taipei. USA: Association for Computational Linguistics. pp. 1–7 doi: 10.18653/v1/2022.aacl-tutorials.1
[15]

Dong J, Zhang Q, Huang X, Duan K, Tan Q, et al. 2023. Hierarchy-aware multi-hop question answering over knowledge graphs. Proceedings of the ACM Web Conference 2023. 30 April–4 May 2023, Austin, TX, USA. USA: Association for Computing Machinery. pp. 2519–2527 doi: 10.1145/3543507.3583376
[16]

Yih WT, Chang MW, He X, Gao J. 2015. Semantic parsing via staged query graph generation: question answering with knowledge base. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 26–31 July 2015. Beijing, China. USA: Association for Computational Linguistics. pp. 1321–1331 https://aclanthology.org/P15-1128.pdf
[17]

Pampari A, Raghavan P, Liang J, Peng J. 2018. emrQA: a large corpus for question answering on electronic medical records. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. October−November 2018. Brussels, Belgium. USA: Association for Computational Linguistics. pp. 2357–2368 doi: 10.18653/v1/D18-1258
[18]

Jin Q, Dhingra B, Liu Z, Cohen W, Lu X. 2019. PubMedQA: a dataset for biomedical research question answering. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). November 2019. Hong Kong, China. USA: Association for Computational Linguistics. pp. 2567–2577 doi: 10.18653/V1/D19-1259
[19]

Saikh T, Ghosal T, Mittal A, Ekbal A, Bhattacharyya P. 2022. ScienceQA: a novel resource for question answering on scholarly articles. International Journal on Digital Libraries 23(3):289−301

doi: 10.1007/S00799-022-00329-Y
[20]

Wellawatte GP, Guo H, Lederbauer M, Borisova A, Hart M, et al. 2025. ChemLit-QA: a human evaluated dataset for chemistry RAG tasks. Machine Learning: Science and Technology 6(2):020601

doi: 10.1088/2632-2153/ADC2D6
[21]

Phan L, Gatti A, Han Z, Li N, Hu J, et al. 2025. Humanity's last exam. arXiv Preprint:2501.14249

doi: 10.48550/ARXIV.2501.14249
[22]

Bai Y, Tu S, Zhang J, Peng H, Wang X, et al. 2025. LongBench v2: towards deeper understanding and reasoning on realistic long-context multitasks. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). July 2025. Vienna, Austria. USA: Association for Computational Linguistics. pp. 3639–3664 doi: 10.18653/v1/2025.acl-long.183
[23]

Skarlinski MD, Cox S, Laurent JM, Braza JD, Hinks M, et al. 2024. Language agents achieve superhuman synthesis of scientific knowledge. arXiv Preprint:2409.13740

doi: 10.48550/ARXIV.2409.13740
[24]

Lee Y, Lee K, Park S, Hwang D, Kim J, et al. 2023. QASA: advanced question answering on scientific articles. Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research (PMLR) 202. 23–29 July 2023. Honolulu, Hawaii, USA. USA: PMLR. pp. 19036–19052 https://openreview.net/pdf?id=5ud0h8OXwD
[25]

Wan Y, Liu Y, Ajith A, Grazian C, Hoex B, et al. 2024. SciQAG: a framework for auto-generated science question answering dataset with fine-grained evaluation. arXiv Preprint:2405.09939

doi: 10.48550/arXiv.2405.09939
[26]

Wei X, Cui X, Cheng N, Wang X, Zhang X, et al. 2023. ChatIE: zero-shot information extraction via chatting with ChatGPT. arXiv Preprint:2302.1020

doi: 10.48550/arXiv.2302.10205
[27]

Yu J, Tang Y, Feng K, Liang L, Zhang Q, et al. 2026. SciCUEval: a comprehensive dataset for evaluating scientific context understanding in large language models. Scientific Data 13:530

doi: 10.1038/s41597-026-06594-9
[28]

Kim MW, Park HB, Ahn HJ, Park WR, Jeon JW, et al. 2025. AutoPaperBench: an MLLM-based framework for automatic generation of paper understanding evaluation benchmarks. Electronics 14(6):1175

doi: 10.3390/electronics14061175
[29]

Luan Y, He L, Ostendorf M, Hajishirzi H. 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. October–November 2018. Brussels, Belgium. USA: Association for Computational Linguistics. pp. 3219–3232 doi: 10.18653/v1/D18-1360
[30]

Yao Y, Ye D, Li P, Han X, Lin Y, et al. 2019. DocRED: a large-scale document-level relation extraction dataset. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. July 2019. Florence, Italy. USA: Association for Computational Linguistics. pp. 764–777 doi: 10.18653/v1/p19-1074
[31]

Xue L, Zhang D, Dong Y, Tang J. 2024. AutoRE: document-level relation extraction with large language models. arXiv Preprint:2403.14888

doi: 10.48550/arXiv.2403.14888
[32]

Wan Z, Cheng F, Mao Z, Liu Q, Song H, et al. 2023. GPT-RE: in-context learning for relation extraction using large language models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. December 2023. Singapore. USA: Association for Computational Linguistics. pp. 3534–3547 doi: 10.18653/V1/2023.EMNLP-MAIN.214.
[33]

Li P, Sun T, Tang Q, Yan H, Wu Y, et al. 2023. CodeIE: large code generation models are better few-shot information extractors. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). July 2023. Toronto, Canada. USA: Association for Computational Linguistics. pp. 15339–15353 doi: 10.18653/V1/2023.ACL-LONG.855.
[34]

Jiao Y, Zhong M, Li S, Zhao R, Ouyang S, et al. 2023. Instruct and extract: instruction tuning for on-demand information extraction. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. December 2023. Singapore. USA: Association for Computational Linguistics. pp. 10030–10051 doi: 10.18653/V1/2023.EMNLP-MAIN.620.
[35]

Lu Y, Liu Q, Dai D, Xiao X, Lin H, et al. 2022. Unified structure generation for universal information extraction. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). May 2022. Dublin, Ireland. USA: Association for Computational Linguistics. pp. 5755–5772 doi: 10.18653/v1/2022.acl-long.395
[36]

Li Z, Zeng Y, Zuo Y, Ren W, Liu W, et al. 2024. KnowCoder: coding structured knowledge into llms for universal information extraction. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). August 2024. Bangkok, Thailand. USA: Association for Computational Linguistics. pp. 8758–8779 doi: 10.18653/V1/2024.ACL-LONG.475.
[37]

Sainz O, García-Ferrero I, Agerri R, de Lacalle OL, Rigau G, et al. 2024. GoLLIE: annotation guidelines improve zero-shot information-extraction. arXiv Preprint:2310.03668

doi: 10.48550/arXiv.2310.03668
[38]

Gao S, Yu K, Yang Y, Yu S, Shi C, et al. 2025. Large language model powered knowledge graph construction for mental health exploration. Nature Communications 16(1):7526

doi: 10.1038/s41467-025-62781-z
[39]

Han R, Yang C, Peng T, Tiwari P, Wan X, et al. 2023. An empirical study on information extraction using large language models. arXiv Preprint:2305.14450

doi: 10.48550/arXiv.2305.14450
[40]

Liu S, Li Y, Li J, Yang S, Lan Y. 2024. Unleashing the power of large language models in zero-shot relation extraction via self-prompting. Findings of the Association for Computational Linguistics: EMNLP 2024. November 2024. Miami, Florida, USA. USA: Association for Computational Linguistics. pp. 13147–13161 doi: 10.18653/v1/2024.findings-emnlp.769
[41]

Bai J, Fan W, Hu Q, Zong Q, Li C, et al. 2026. AutoSchemaKG: autonomous knowledge graph construction through dynamic schema induction from web-scale corpora. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). July 2026. San Diego, California, USA. USA: Association for Computational Linguistics. pp. 20557–20584 doi: 10.18653/v1/2026.acl-long.942
[42]

Bai J, Bai S, Chu Y, Cui Z, Dang K, et al. 2023. Qwen technical report. arXiv Preprint:2309.16609

doi: 10.48550/arXiv.2309.16609
[43]

DeepSeek-AI. 2024. DeepSeek-V2: a strong, economical, and efficient mixture-of-experts language model. arXiv Preprint:2405.04434

doi: 10.48550/arXiv.2405.04434