thesis_references.bib

% =============================================================================
% 硕士论文 1.1 节引用的参考文献 BibTeX 汇总
% =============================================================================

% [1] GPT-4 Technical Report — OpenAI, 2023
@article{openai2023gpt4,
  title     = {{GPT-4} Technical Report},
  author    = {OpenAI},
  journal   = {arXiv preprint arXiv:2303.08774},
  year      = {2023},
  url       = {https://arxiv.org/abs/2303.08774}
}

% [2] Gemini 1.5 — Google DeepMind, 2024
@article{geminiteam2024gemini15,
  title     = {Gemini 1.5: Unlocking Multimodal Understanding Across Millions of Tokens of Context},
  author    = {{Gemini Team} and Georgiev, Petko and Lei, Ving and Burnell, Ryan and others},
  journal   = {arXiv preprint arXiv:2403.05530},
  year      = {2024},
  url       = {https://arxiv.org/abs/2403.05530}
}

% [3] DeepSeek-V3 Technical Report — DeepSeek-AI, 2024
@article{deepseekai2024deepseekv3,
  title     = {{DeepSeek-V3} Technical Report},
  author    = {{DeepSeek-AI}},
  journal   = {arXiv preprint arXiv:2412.19437},
  year      = {2024},
  url       = {https://arxiv.org/abs/2412.19437}
}

% [4] Hallucination is Inevitable — Xu et al., 2025
@article{xu2025hallucination,
  title     = {Hallucination is Inevitable: An Innate Limitation of Large Language Models},
  author    = {Xu, Ziwei and Jain, Sanjay and Kankanhalli, Mohan},
  journal   = {arXiv preprint arXiv:2401.11817},
  year      = {2025},
  url       = {https://arxiv.org/abs/2401.11817}
}

% [5] Large Language Models Struggle to Learn Tail Knowledge — Kandpal et al., NeurIPS 2023
@inproceedings{kandpal2023largelanguagemodelsstruggle,
  title     = {Large Language Models Struggle to Learn Tail Knowledge},
  author    = {Kandpal, Nikhil and Deng, Haikang and Roberts, Adam and Wallace, Eric and Raffel, Colin},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning (ICML)},
  pages     = {15696--15707},
  year      = {2023},
  publisher = {PMLR},
  url       = {https://arxiv.org/abs/2211.08411}
}

% [6] REALM: Retrieval-Augmented Language Model Pre-Training — Guu et al., ICML 2020
@inproceedings{guu2020realm,
  title     = {{REALM}: Retrieval-Augmented Language Model Pre-Training},
  author    = {Guu, Kelvin and Lee, Kenton and Tung, Zora and Pasupat, Panupong and Chang, Ming-Wei},
  booktitle = {Proceedings of the 37th International Conference on Machine Learning (ICML)},
  pages     = {3929--3938},
  year      = {2020},
  publisher = {PMLR},
  volume    = {119},
  url       = {https://proceedings.mlr.press/v119/guu20a.html}
}

% [7] RAG — Lewis et al., NeurIPS 2020
% Source: researchr.org / NeurIPS proceedings
@inproceedings{lewis2020rag,
  title     = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks},
  author    = {Lewis, Patrick S. H. and Perez, Ethan and Piktus, Aleksandra and Petroni, Fabio and Karpukhin, Vladimir and Goyal, Naman and K{\"u}ttler, Heinrich and Lewis, Mike and Yih, Wen-tau and Rockt{\"a}schel, Tim and Riedel, Sebastian and Kiela, Douwe},
  booktitle = {Advances in Neural Information Processing Systems 33 (NeurIPS)},
  year      = {2020},
  url       = {https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html}
}

% [8] — 统计数据来源，非正式引用，可替换为脚注

% [9] — 行业报告，非正式引用，可替换为脚注

% [10] DPR — Karpukhin et al., EMNLP 2020
% Source: ACL Anthology (aclanthology.org/2020.emnlp-main.550)
@inproceedings{karpukhin-etal-2020-dense,
  title     = {Dense Passage Retrieval for Open-Domain Question Answering},
  author    = {Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau},
  editor    = {Webber, Bonnie and Cohn, Trevor and He, Yulan and Liu, Yang},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month     = nov,
  year      = {2020},
  address   = {Online},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2020.emnlp-main.550/},
  doi       = {10.18653/v1/2020.emnlp-main.550},
  pages     = {6769--6781}
}

% [11] Contriever — Izacard et al., TMLR 2022
@article{izacard2022contriever,
  title     = {Unsupervised Dense Information Retrieval with Contrastive Learning},
  author    = {Izacard, Gautier and Caron, Mathilde and Hosseini, Lucas and Riedel, Sebastian and Bojanowski, Piotr and Joulin, Armand and Grave, Edouard},
  journal   = {Transactions on Machine Learning Research (TMLR)},
  year      = {2022},
  url       = {https://openreview.net/forum?id=jKN1pXi7b0}
}

% [12] C-Pack / BGE — Xiao et al., 2023
@article{xiao2023cpack,
  title     = {{C-Pack}: Packaged Resources to Advance General {C}hinese Embedding},
  author    = {Xiao, Shitao and Liu, Zheng and Zhang, Peitian and Muennighoff, Niklas},
  journal   = {arXiv preprint arXiv:2309.07597},
  year      = {2023},
  url       = {https://arxiv.org/abs/2309.07597}
}

% [13] QuAC — Choi et al., EMNLP 2018
% Source: ACL Anthology (aclanthology.org/D18-1241)
@inproceedings{choi-etal-2018-quac,
  title     = {{Q}u{AC}: Question Answering in Context},
  author    = {Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},
  editor    = {Riloff, Ellen and Chiang, David and Hockenmaier, Julia and Tsujii, Jun{'}ichi},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month     = oct # {-} # nov,
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/D18-1241/},
  doi       = {10.18653/v1/D18-1241},
  pages     = {2174--2184}
}

% [14] CoQA — Reddy et al., TACL 2019
@article{reddy-etal-2019-coqa,
  title     = {{CoQA}: A Conversational Question Answering Challenge},
  author    = {Reddy, Siva and Chen, Danqi and Manning, Christopher D.},
  journal   = {Transactions of the Association for Computational Linguistics},
  volume    = {7},
  pages     = {249--266},
  year      = {2019},
  publisher = {MIT Press},
  doi       = {10.1162/tacl_a_00266},
  url       = {https://aclanthology.org/Q19-1016/}
}

% [15] Doc2Dial — Feng et al., EMNLP 2020
@inproceedings{feng-etal-2020-doc2dial,
  title     = {doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset},
  author    = {Feng, Song and Wan, Hui and Gunasekara, Chulaka and Patel, Siva Sankalp and Joshi, Sachindra and Lastras, Luis A.},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month     = nov,
  year      = {2020},
  address   = {Online},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2020.emnlp-main.652/},
  doi       = {10.18653/v1/2020.emnlp-main.652},
  pages     = {8118--8128}
}

% [16] QReCC — Anantha et al., NAACL 2021
@inproceedings{anantha-etal-2021-qrecc,
  title     = {Open-Domain Question Answering Goes Conversational via Question Rewriting},
  author    = {Anantha, Raviteja and Vakulenko, Svitlana and Tu, Zhucheng and Altber, Shayne and Cop, Saab and Reimers, Nils},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)},
  year      = {2021},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2021.naacl-main.44/},
  doi       = {10.18653/v1/2021.naacl-main.44},
  pages     = {520--534}
}

% [17] Zobel 1998 — How Reliable Are the Results of Large-Scale IR Experiments
@inproceedings{zobel1998reliable,
  title     = {How Reliable Are the Results of Large-Scale Information Retrieval Experiments?},
  author    = {Zobel, Justin},
  booktitle = {Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
  year      = {1998},
  pages     = {307--314},
  publisher = {ACM},
  doi       = {10.1145/290941.291014},
  url       = {https://dl.acm.org/doi/10.1145/290941.291014}
}

% [18] Buckley & Voorhees 2004 — Retrieval Evaluation with Incomplete Information
% Source: BibSLEIGH (bibtex.github.io/SIGIR-2004-BuckleyV.html)
@inproceedings{buckley2004retrieval,
  title     = {Retrieval Evaluation with Incomplete Information},
  author    = {Buckley, Chris and Voorhees, Ellen M.},
  booktitle = {Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
  year      = {2004},
  pages     = {25--32},
  publisher = {ACM},
  isbn      = {1-58113-881-4},
  doi       = {10.1145/1008992.1009000}
}

% [19] CORAL — Cheng et al., 2025
@article{coral2025,
  title     = {{CORAL}: Benchmarking Multi-Turn Conversational Retrieval-Augmented Generation},
  author    = {Cheng, Yiruo and Choi, Helia and Fang, Silvio and Patel, Daven and Xiong, Chenyan},
  journal   = {arXiv preprint arXiv:2410.23090},
  year      = {2024},
  url       = {https://arxiv.org/abs/2410.23090}
}

% [20] InstructGPT / RLHF — Ouyang et al., NeurIPS 2022
% Source: NeurIPS official .bib
@inproceedings{ouyang2022traininglanguagemodelsfollow,
  author    = {Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and Schulman, John and Hilton, Jacob and Kelton, Fraser and Miller, Luke and Simens, Maddie and Askell, Amanda and Welinder, Peter and Christiano, Paul F and Leike, Jan and Lowe, Ryan},
  booktitle = {Advances in Neural Information Processing Systems},
  editor    = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
  pages     = {27730--27744},
  publisher = {Curran Associates, Inc.},
  title     = {Training language models to follow instructions with human feedback},
  url       = {https://proceedings.neurips.cc/paper_files/paper/2022/file/b1efde53be364a73914f58805a001731-Paper-Conference.pdf},
  volume    = {35},
  year      = {2022}
}


@article{gao2024retrievalaugmented,
  author    = {Yunfan Gao and Yun Xiong and Xinyu Gao and Kangxiang Jia and Jinliu Pan and Yuxi Bi and Yi Dai and Jiawei Sun and Qianyu Guo and Meng Wang and Haofen Wang},
  title     = {Retrieval-Augmented Generation for Large Language Models: A Survey},
  journal   = {CoRR},
  volume    = {abs/2312.10997},
  year      = {2023},
  url       = {https://arxiv.org/abs/2312.10997},
  eprinttype = {arXiv},
  eprint    = {2312.10997}
}

@inproceedings{shuster2021retrieval,
  author    = {Kurt Shuster and Spencer Poff and Moya Chen and Douwe Kiela and Jason Weston},
  title     = {Retrieval Augmentation Reduces Hallucination in Conversation},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
  pages     = {3784--3803},
  publisher = {Association for Computational Linguistics},
  year      = {2021},
  url       = {https://aclanthology.org/2021.findings-emnlp.320}
}