---
title: "Source-Aware Training Enables Knowledge Attribution in"
description: "The authors propose a two-step recipe called source-aware training. 56 references, cited by 20 papers here."
authors: ["Muhammad Khalifa", "David Wadden", "Emma Strubell", "Honglak Lee", "Lu Wang", "Iz Beltagy", "Hao Peng"]
year: 2024
venue: "arXiv:2404.01019"
source: "https://arxiv.org/abs/2404.01019"
doi: "10.48550/arxiv.2404.01019"
arxiv: "2404.01019"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/khalifa-2024-source-aware-training-enables-knowledge/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/khalifa-2024-source-aware-training-enables-knowledge/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/) / Source-Aware Training Enables Knowledge Attribution in Language Models

# Source-Aware Training Enables Knowledge Attribution in Language Models

**Authors:** [Muhammad Khalifa](https://md.research.elamur.ai/free/en/authors/muhammad-khalifa/), [David Wadden](https://md.research.elamur.ai/free/en/authors/david-wadden/), [Emma Strubell](https://md.research.elamur.ai/free/en/authors/emma-strubell/), [Honglak Lee](https://md.research.elamur.ai/free/en/authors/honglak-lee/), [Lu Wang](https://md.research.elamur.ai/free/en/authors/lu-wang/), [Iz Beltagy](https://md.research.elamur.ai/free/en/authors/iz-beltagy/) and [Hao Peng](https://md.research.elamur.ai/free/en/authors/hao-peng/) · **Year:** 2024 · **Venue:** arXiv:2404.01019 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2404.01019) · [PDF](https://arxiv.org/pdf/2404.01019) · [DOI 10.48550/arxiv.2404.01019](https://doi.org/10.48550/arxiv.2404.01019) · [arXiv 2404.01019](https://arxiv.org/abs/2404.01019) · [OpenAlex](https://openalex.org/W4393733730)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [20](https://md.research.elamur.ai/free/en/papers/khalifa-2024-source-aware-training-enables-knowledge/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLMs absorb large amounts of factual knowledge during pretraining but cannot say which documents it came from. This paper studies *intrinsic source citation*: the model itself names the pretraining document behind its answer, without retrieval or post-hoc evidence search. The authors propose a two-step recipe called source-aware training. First, an off-the-shelf model is continually pretrained on a corpus in which every document carries a unique identifier. Second, the model is instruction-tuned to answer questions and output the identifier of a supporting document. Instruction tuning uses only part of the corpus (in-domain), and attribution is tested on documents seen only during pretraining (out-of-domain).

Experiments use BioCite, a synthetic corpus of fictitious biographies. The model can attribute out-of-domain knowledge reasonably well, with little perplexity cost compared to ordinary pretraining. This only works when documents are augmented by shuffling their facts into several versions. The work is a small-scale proof of concept. It points toward more verifiable and transparent LLMs and toward better ways to audit pretraining data.

## Key points
- **Identifiers and injection:** Doc IDs are built from truncated last names (e.g., `rod-bus-goo-val`) and injected into pretraining text; REPEAT is one of the injection strategies tested.
- **Augmentation:** Document-level augmentation (permuting facts N_aug times) is needed for out-of-domain Hits@1. Fact-level augmentation raises answer match but leaves citation accuracy unchanged. Citation becomes more difficult as the number of facts a document contains grows.
- **ID design (BioCite, REPEAT):**

  | Doc ID type | OOD EM | Hits@1 |
  |---|---|---|
  | Last-name IDs | 88.8 | 47.3 |
  | Random 8-digit IDs | 95.9 | 39.8 |

- **No last-name shortcut:** Across 352K pairs of questions about people sharing a surname, the mean Jaccard overlap of their top-10 predicted IDs is only 0.08. This suggests the model relies on fact content rather than guessing from the surname.
- **Limitations and code:** The study uses synthetic data, small models and corpora, and augmentation adds pretraining cost. Code and data are at github.com/mukhal/intrinsic-source-citation.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 275 works · 97,634 citations
- [University of Illinois Urbana-Champaign](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) — University, Urbana, United States · 184 works · 69,372 citations
- [University of Michigan](https://md.research.elamur.ai/free/en/universities/university-of-michigan/) — University, Ann Arbor, United States · 70 works · 13,693 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Muhammad Khalifa, David Wadden, Emma Strubell, Honglak Lee, Lu Wang, Iz Beltagy and Hao Peng. 2024. Source-Aware Training Enables Knowledge Attribution in Language Models. arXiv:2404.01019.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{khalifa2024source,
  title = {{Source-Aware Training Enables Knowledge Attribution in Language Models}},
  author = {Muhammad Khalifa, David Wadden, Emma Strubell, Honglak Lee, Lu Wang, Iz Beltagy and Hao Peng},
  year = {2024},
  doi = {10.48550/arxiv.2404.01019},
  eprint = {2404.01019},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2404.01019}
}
```

- [← previous Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models](https://md.research.elamur.ai/free/en/papers/wei-2024-skywork-moe-deep-dive/)
- [next → SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://md.research.elamur.ai/free/en/papers/ma-2024-spreadsheetbench-towards-challenging-real-world/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/)

## References

56 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ayush Agrawal, Lester Mackey, and Adam Tauman Kalai. Do language models know when they’re hallucinating references? CoRR, abs/2305.18248, 2023. doi: 10.48550/ARXIV.2305. 18248. URL https://doi.org/10.48550/arXiv.2305.18248. [↗](https://doi.org/10.48550/arXiv.2305.18248)
2. Zeyuan Allen-Zhu and Yuanzhi Li. Physics of language models: Part 3.2, knowledge manipulation. CoRR, abs/2309.14402, 2023. doi: 10.48550/ARXIV.2309.14402. URL https://doi.org/10.48550/arXiv.2309.14402. [↗](https://doi.org/10.48550/arXiv.2309.14402)
3. David Alvarez Melis and Tommi Jaakkola. Towards robust interpretability with self-explaining neural networks. Advances in neural information processing systems, 31, 2018. [find](https://scholar.google.com/scholar?q=David+Alvarez+Melis+and+Tommi+Jaakkola%2E+Towards+robust+interpretability+with+self%2Dexplaining+neural+networks%2E+Advances+in+neural+information+processing+systems%2C+31%2C+2018%2E)
4. Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans. The reversal curse: Llms trained on” a is b” fail to learn” b is a”. arXiv preprint arXiv:2309.12288, 2023. [find](https://scholar.google.com/scholar?q=Lukas+Berglund%2C+Meg+Tong%2C+Max+Kaufmann%2C+Mikita+Balesni%2C+Asa+Cooper+Stickland%2C+Tomasz+Korbak%2C+and+Owain+Evans%2E+The+reversal+curse%3A+Llms+trained+on%E2%80%9D+a+is+b%E2%80%9D+fail+to+learn%E2%80%9D+b+is+a%E2%80%9D%2E+arXiv+preprint+arXiv%3A)
5. Bernd Bohnet, Vinh Q Tran, Pat Verga, Roee Aharoni, Daniel Andor, Livio Baldini Soares, Massimiliano Ciaramita, Jacob Eisenstein, Kuzman Ganchev, Jonathan Herzig, et al. [Attributed question answering: Evaluation and modeling for attributed large language models](https://md.research.elamur.ai/free/en/papers/bohnet-2022-attributed-question-answering-evaluation-modeling/). arXiv preprint arXiv:2212.08037, 2022…
6. Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cas… [find](https://scholar.google.com/scholar?q=Sebastian+Borgeaud%2C+Arthur+Mensch%2C+Jordan+Hoffmann%2C+Trevor+Cai%2C+Eliza+Rutherford%2C+Katie+Millican%2C+George+van+den+Driessche%2C+Jean%2DBaptiste+Lespiau%2C+Bogdan+Damoc%2C+Aidan+Clark%2C+Diego+de+Las+Casas%2C+Aureli)
7. PMLR, 2022. URL [https://proceedings.mlr.press/v162/borgeaud22a.html](https://proceedings.mlr.press/v162/borgeaud22a.html). [↗](https://proceedings.mlr.press/v162/borgeaud22a.html)
8. Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. Autoregressive entity retrieval. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. [find](https://scholar.google.com/scholar?q=Nicola+De+Cao%2C+Gautier+Izacard%2C+Sebastian+Riedel%2C+and+Fabio+Petroni%2E+Autoregressive+entity+retrieval%2E+In+9th+International+Conference+on+Learning+Representations%2C+ICLR+2021%2C+Virtual+Event%2C+Austria%2C+Ma)
9. OpenReview.net, 2021. URL [https://openreview.net/](https://openreview.net/) forum?id=5k8F6UU39V. [↗](https://openreview.net/)
10. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). Journal of Machine Learning Research, 24(240):1–113, 2023.
11. Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Y. Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. [RARR: researching and revising what language models say, using language models](https://md.research.elamur.ai/free/en/papers/gao-2023-rarr-researching-revising-what-language/). In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (ed…
12. Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. [Enabling large language models to generate text with citations](https://md.research.elamur.ai/free/en/papers/gao-2023-enabling-large-language-models-generate/). In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023,…
13. Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A Smith. [Realtoxicityprompts: Evaluating neural toxic degeneration in language models](https://md.research.elamur.ai/free/en/papers/gehman-2020-realtoxicityprompts-evaluating-neural-toxic-degeneration/). arXiv preprint arXiv:2009.11462, 2020.
14. Roger Grosse, Juhan Bae, Cem Anil, Nelson Elhage, Alex Tamkin, Amirhossein Tajdini, Benoit Steiner, Dustin Li, Esin Durmus, Ethan Perez, et al. Studying large language model generalization with influence functions. arXiv preprint arXiv:2308.03296, 2023. [find](https://scholar.google.com/scholar?q=Roger+Grosse%2C+Juhan+Bae%2C+Cem+Anil%2C+Nelson+Elhage%2C+Alex+Tamkin%2C+Amirhossein+Tajdini%2C+Benoit+Steiner%2C+Dustin+Li%2C+Esin+Durmus%2C+Ethan+Perez%2C+et+al%2E+Studying+large+language+model+generalization+with+influe)
15. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. Retrieval augmented language model pre-training. In International conference on machine learning, pp. 3929–3938. PMLR, 2020. — [REALM: Retrieval-Augmented Language Model Pre-Training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/)
16. Hangfeng He, Hongming Zhang, and Dan Roth. Rethinking with retrieval: Faithful large language model inference. CoRR, abs/2301.00303, 2023. doi: 10.48550/ARXIV.2301.00303. URL https://doi.org/10.48550/arXiv.2301.00303. [↗](https://doi.org/10.48550/arXiv.2301.00303)
17. Jie Huang and Kevin Chen-Chuan Chang. Citation: A key to building responsible and accountable large language models. CoRR, abs/2307.02185, 2023. doi: 10.48550/ARXIV. 2307.02185. URL https://doi.org/10.48550/arXiv.2307.02185. [↗](https://doi.org/10.48550/arXiv.2307.02185)
18. Gautier Izacard, Patrick S. H. Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. [Atlas: Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). J. Mach. Learn. Res., 24: 251:1–251:43, 2023. URL [http://jmlr.org/pa…](http://jmlr.org/pa…) [↗](http://jmlr.org/pa…)
19. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12):1–38, 2023.
20. Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, and Seong Joon Oh. Propile: Probing privacy leakage in large language models. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=Siwon+Kim%2C+Sangdoo+Yun%2C+Hwaran+Lee%2C+Martin+Gubri%2C+Sungroh+Yoon%2C+and+Seong+Joon+Oh%2E+Propile%3A+Probing+privacy+leakage+in+large+language+models%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%2C+202)
21. Pang Wei Koh and Percy Liang. Understanding black-box predictions via influence functions. In International conference on machine learning, pp. 1885–1894. [find](https://scholar.google.com/scholar?q=Pang+Wei+Koh+and+Percy+Liang%2E+Understanding+black%2Dbox+predictions+via+influence+functions%2E+In+International+conference+on+machine+learning%2C+pp%2E+1885%E2%80%931894%2E)
22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in Neural Information Processing Systems, 33:9459–9474, 2020.
23. Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix X. Yu, and Sanjiv Kumar. [Large language models with controllable working memory](https://md.research.elamur.ai/free/en/papers/li-2023-large-language-models-controllable-working/). In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (eds.), Findings of the Association for Computational Linguistics: AC…
24. Dongfang Li, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Ziyang Chen, Baotian Hu, Aiguo Wu, and Min Zhang. A survey of large language models attribution. arXiv preprint arXiv:2311.03731, 2023b. — [arXiv:2311.03731](https://arxiv.org/abs/2311.03731) [find](https://scholar.google.com/scholar?q=Dongfang+Li%2C+Zetian+Sun%2C+Xinshuo+Hu%2C+Zhenyu+Liu%2C+Ziyang+Chen%2C+Baotian+Hu%2C+Aiguo+Wu%2C+and+Min+Zhang%2E+A+survey+of+large+language+models+attribution%2E+arXiv+preprint+arXiv%3A2311%2E03731%2C+2023b%2E+%E2%80%94+%5BarXiv%3A2311%2E)
25. Nelson F. Liu, Tianyi Zhang, and Percy Liang. [Evaluating verifiability in generative search engines](https://md.research.elamur.ai/free/en/papers/liu-2023-evaluating-verifiability-generative-search-engines/). In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pp. 7001–7025. Association for Computationa…
26. Shayne Longpre, Robert Mahari, Anthony Chen, Naana Obeng-Marnu, Damien Sileo, William Brannon, Niklas Muennighoff, Nathan Khazam, Jad Kabbara, Kartik Perisetla, et al. The data provenance initiative: A large scale audit of dataset licensing & attribution in ai. arXiv preprint arXiv:2310.16787, 2023. — [arXiv:2310.16787](https://arxiv.org/abs/2310.16787) [find](https://scholar.google.com/scholar?q=Shayne+Longpre%2C+Robert+Mahari%2C+Anthony+Chen%2C+Naana+Obeng%2DMarnu%2C+Damien+Sileo%2C+William+Brannon%2C+Niklas+Muennighoff%2C+Nathan+Khazam%2C+Jad+Kabbara%2C+Kartik+Perisetla%2C+et+al%2E+The+data+provenance+initiative%3A+)
27. Kelvin Luu, Rik Koncel-Kedziorski, Kyle Lo, Isabel Cachola, and Noah A. Smith. Citation text generation. ArXiv, abs/2002.00317, 2020. URL [https://api.semanticscholar.org/](https://api.semanticscholar.org/) CorpusID:211010521. — [arXiv:2002.00317](https://arxiv.org/abs/2002.00317) [↗](https://api.semanticscholar.org/)
28. Ana Marasovic, Iz Beltagy, Doug Downey, and Matthew E. Peters. [Few-shot self-rationalization with natural language prompts](https://md.research.elamur.ai/free/en/papers/marasovic-2022-few-shot-self-rationalization-natural/). In Marine Carpuat, Marie-Catherine de Marneffe, and Iván Vladimir Meza Ruı́z (eds.), Findings of the Association for Computational Linguistics: NAACL 2022, Seattle, WA, United…
29. Sean M McNee, Istvan Albert, Dan Cosley, Prateep Gopalkrishnan, Shyong K Lam, Al Mamunur Rashid, Joseph A Konstan, and John Riedl. On the recommending of citations for research papers. In Proceedings of the 2002 ACM conference on Computer supported cooperative work, pp. 116–125, 2002. [find](https://scholar.google.com/scholar?q=Sean+M+McNee%2C+Istvan+Albert%2C+Dan+Cosley%2C+Prateep+Gopalkrishnan%2C+Shyong+K+Lam%2C+Al+Mamunur+Rashid%2C+Joseph+A+Konstan%2C+and+John+Riedl%2E+On+the+recommending+of+citations+for+research+papers%2E+In+Proceedings+)
30. Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, et al. [Teaching language models to support answers with verified quotes](https://md.research.elamur.ai/free/en/papers/menick-2022-teaching-language-models-support-answers/). arXiv preprint arXiv:2203.11147, 2022.
31. Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. [Pointer sentinel mixture models](https://md.research.elamur.ai/free/en/papers/merity-2016-pointer-sentinel-mixture-models/). In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
32. OpenReview.net, 2017. URL [https://openreview.net/forum?id=Byj72udxe](https://openreview.net/forum?id=Byj72udxe). [↗](https://openreview.net/forum?id=Byj72udxe)
33. Sewon Min, Suchin Gururangan, Eric Wallace, Hannaneh Hajishirzi, Noah A Smith, and Luke Zettlemoyer. Silo language models: Isolating legal risk in a nonparametric datastore. arXiv preprint arXiv:2308.04430, 2023. [find](https://scholar.google.com/scholar?q=Sewon+Min%2C+Suchin+Gururangan%2C+Eric+Wallace%2C+Hannaneh+Hajishirzi%2C+Noah+A+Smith%2C+and+Luke+Zettlemoyer%2E+Silo+language+models%3A+Isolating+legal+risk+in+a+nonparametric+datastore%2E+arXiv+preprint+arXiv%3A2308%2E)
34. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. Webgpt: Browser-assisted qu… — [WebGPT: Browser-assisted question-answering with human feedback](https://md.research.elamur.ai/free/en/papers/nakano-2021-webgpt-browser-assisted-question-answering/)
35. Ramesh M Nallapati, Amr Ahmed, Eric P Xing, and William W Cohen. Joint latent topic models for text and citations. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 542–550, 2008. [find](https://scholar.google.com/scholar?q=Ramesh+M+Nallapati%2C+Amr+Ahmed%2C+Eric+P+Xing%2C+and+William+W+Cohen%2E+Joint+latent+topic+models+for+text+and+citations%2E+In+Proceedings+of+the+14th+ACM+SIGKDD+international+conference+on+Knowledge+discovery)
36. Maxwell I. Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, and Augustus Odena. [Show your work: Scratchpads for intermediate computation with language models](https://md.research.elamur.ai/free/en/papers/al-2021-show-your-work-scratchpads-intermediate/). CoRR, abs/2112.00114, 2021…
37. Fabio Petroni, Patrick S. H. Lewis, Aleksandra Piktus, Tim Rocktäschel, Yuxiang Wu, Alexander H. Miller, and Sebastian Riedel. How context affects language models’ factual predictions. In Dipanjan Das, Hannaneh Hajishirzi, Andrew McCallum, and Sameer Singh (eds.), Conference on Automated Knowledge… — [How Context Affects Language Models' Factual Predictions](https://md.research.elamur.ai/free/en/papers/petroni-2020-context-affects-language-models-factual/)
38. Ronak Pradeep, Kai Hui, Jai Gupta, Adam D Lelkes, Honglei Zhuang, Jimmy Lin, Donald Metzler, and Vinh Q Tran. How does generative retrieval scale to millions of passages? arXiv preprint arXiv:2305.11841, 2023. [find](https://scholar.google.com/scholar?q=Ronak+Pradeep%2C+Kai+Hui%2C+Jai+Gupta%2C+Adam+D+Lelkes%2C+Honglei+Zhuang%2C+Jimmy+Lin%2C+Donald+Metzler%2C+and+Vinh+Q+Tran%2E+How+does+generative+retrieval+scale+to+millions+of+passages%3F+arXiv+preprint+arXiv%3A2305%2E118)
39. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2C+2019%2E)
40. Hannah Rashkin, Vitaly Nikolaev, Matthew Lamm, Lora Aroyo, Michael Collins, Dipanjan Das, Slav Petrov, Gaurav Singh Tomar, Iulia Turc, and David Reitter. [Measuring attribution in natural language generation models](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/). Computational Linguistics, pp. 1–66, 2023.
41. Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. Detecting pretraining data from large language models. arXiv preprint arXiv:2310.16789, 2023. [find](https://scholar.google.com/scholar?q=Weijia+Shi%2C+Anirudh+Ajith%2C+Mengzhou+Xia%2C+Yangsibo+Huang%2C+Daogao+Liu%2C+Terra+Blevins%2C+Danqi+Chen%2C+and+Luke+Zettlemoyer%2E+Detecting+pretraining+data+from+large+language+models%2E+arXiv+preprint+arXiv%3A2310%2E1)
42. Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten Rijke, and Zhaochun Ren. Learning to tokenize for generative retrieval. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=Weiwei+Sun%2C+Lingyong+Yan%2C+Zheng+Chen%2C+Shuaiqiang+Wang%2C+Haichao+Zhu%2C+Pengjie+Ren%2C+Zhumin+Chen%2C+Dawei+Yin%2C+Maarten+Rijke%2C+and+Zhaochun+Ren%2E+Learning+to+tokenize+for+generative+retrieval%2E+Advances+in+Neu)
43. Yi Tay, Vinh Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Prakash Gupta, Tal Schuster, William W. Cohen, and Donald Metzler. [Transformer memory as a differentiable search index](https://md.research.elamur.ai/free/en/papers/tay-2022-transformer-memory-differentiable-search-index/). In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A.…
44. Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. [Galactica: A large language model for science](https://md.research.elamur.ai/free/en/papers/taylor-2022-galactica-large-language-model-science/). arXiv preprint arXiv:2211.09085, 2022.
45. Yujing Wang, Yingyan Hou, Haonan Wang, Ziming Miao, Shibin Wu, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, et al. A neural corpus indexer for document retrieval. Advances in Neural Information Processing Systems, 35:25600–25614, 2022. [find](https://scholar.google.com/scholar?q=Yujing+Wang%2C+Yingyan+Hou%2C+Haonan+Wang%2C+Ziming+Miao%2C+Shibin+Wu%2C+Qi+Chen%2C+Yuqing+Xia%2C+Chengmin+Chi%2C+Guoshuai+Zhao%2C+Zheng+Liu%2C+et+al%2E+A+neural+corpus+indexer+for+document+retrieval%2E+Advances+in+Neural+In)
46. Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). arXiv preprint arXiv:2109.01652, 2021.
47. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
48. Orion Weller, Marc Marone, Nathaniel Weir, Dawn Lawrie, Daniel Khashabi, and Benjamin Van Durme. ” according to...” prompting language models improves quoting from pre-training data. arXiv preprint arXiv:2305.[13252, 2023](https://md.research.elamur.ai/free/en/papers/weller-2024-according-prompting-language-models-improves/).
49. Xinyu Xing, Xiaosheng Fan, and Xiaojun Wan. Automatic generation of citation texts in scholarly papers: A pilot study. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel Tetreault (eds.), Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6181–6190, Onl… [find](https://scholar.google.com/scholar?q=Xinyu+Xing%2C+Xiaosheng+Fan%2C+and+Xiaojun+Wan%2E+Automatic+generation+of+citation+texts+in+scholarly+papers%3A+A+pilot+study%2E+In+Dan+Jurafsky%2C+Joyce+Chai%2C+Natalie+Schluter%2C+and+Joel+Tetreault+%28eds%2E%29%2C+Proceed)
50. Hongbin Ye, Tong Liu, Aijia Zhang, Wei Hua, and Weiqiang Jia. Cognitive mirage: A review of hallucinations in large language models. CoRR, abs/2309.06794, 2023a. doi: 10.48550/ARXIV.2309.06794. URL https://doi.org/10.48550/arXiv.2309.06794. — [doi:10.48550/arxiv.2309.06794](https://doi.org/10.48550/arxiv.2309.06794) [↗](https://doi.org/10.48550/arXiv.2309.06794)
51. Xi Ye, Ruoxi Sun, Sercan Ö Arik, and Tomas Pfister. Effective large language model adaptation for improved grounding. arXiv preprint arXiv:2311.09533, 2023b. — [arXiv:2311.09533](https://arxiv.org/abs/2311.09533) [find](https://scholar.google.com/scholar?q=Xi+Ye%2C+Ruoxi+Sun%2C+Sercan+O%CC%88+Arik%2C+and+Tomas+Pfister%2E+Effective+large+language+model+adaptation+for+improved+grounding%2E+arXiv+preprint+arXiv%3A2311%2E09533%2C+2023b%2E+%E2%80%94+%5BarXiv%3A2311%2E09533%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
52. Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, and Wei Lu. [Tinyllama: An open-source small language model](https://md.research.elamur.ai/free/en/papers/zhang-2024-tinyllama-open-source-small-language/). arXiv preprint arXiv:2401.02385, 2024.
53. Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, et al. [Instruction tuning for large language models: A survey](https://md.research.elamur.ai/free/en/papers/zhang-2023-instruction-tuning-large-language-models/). arXiv preprint arXiv:2308.10792, 2023.
54. Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. Lima: Less is more for alignment. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srinivasan+Iyer%2C+Jiao+Sun%2C+Yuning+Mao%2C+Xuezhe+Ma%2C+Avia+Efrat%2C+Ping+Yu%2C+Lili+Yu%2C+et+al%2E+Lima%3A+Less+is+more+for+alignment%2E+Advances+in+Neural+Information+Processing)
55. Zeyuan Allen Zhu and Yuanzhi Li. [Physics of language models: Part 3.1, knowledge storage and extraction](https://md.research.elamur.ai/free/en/papers/allen-zhu-2023-physics-language-models-part-3/). CoRR, abs/2309.14316, 2023. doi: 10.48550/ARXIV.2309.14316. URL https://doi.org/10.48550/arXiv.2309.14316. [↗](https://doi.org/10.48550/arXiv.2309.14316)
56. Guido Zuccon, Bevan Koopman, and Razia Shaik. Chatgpt hallucinates when attributing answers. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pp. 46–51, 2023. [find](https://scholar.google.com/scholar?q=Guido+Zuccon%2C+Bevan+Koopman%2C+and+Razia+Shaik%2E+Chatgpt+hallucinates+when+attributing+answers%2E+In+Proceedings+of+the+Annual+International+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+)

*Updated 30 October 2026*