---
title: "Reviewer2 — paper by Gao et al. (2024) — summary and ideas"
description: "To fix this, the authors propose REVIEWER2, a two-stage system: one fine-tuned model reads the… 45 references, cited by 24 papers here."
authors: ["Zhaolin Gao", "Kiante Brantley", "Thorsten Joachims"]
year: 2024
venue: "arXiv:2402.10886"
source: "https://arxiv.org/abs/2402.10886"
doi: "10.48550/arxiv.2402.10886"
arxiv: "2402.10886"
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/gao-2024-reviewer2-optimizing-review-generation-through/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gao-2024-reviewer2-optimizing-review-generation-through/)

[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/7/) / Reviewer2: Optimizing Review Generation Through Prompt Generation

# Reviewer2: Optimizing Review Generation Through Prompt Generation

**Authors:** Zhaolin Gao, [Kiante Brantley](https://md.research.elamur.ai/free/en/authors/kiante-brantley/) and [Thorsten Joachims](https://md.research.elamur.ai/free/en/authors/thorsten-joachims/) · **Year:** 2024 · **Venue:** arXiv:2402.10886 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2402.10886) · [PDF](https://arxiv.org/pdf/2402.10886) · [DOI 10.48550/arxiv.2402.10886](https://doi.org/10.48550/arxiv.2402.10886) · [arXiv 2402.10886](https://arxiv.org/abs/2402.10886) · [OpenAlex](https://openalex.org/W4391949093)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [24](https://md.research.elamur.ai/free/en/papers/gao-2024-reviewer2-optimizing-review-generation-through/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Authors without many colleagues to critique their drafts have few chances to get feedback before formal peer review. The paper asks whether LLMs can fill this gap. It finds that plain fine-tuning on paper–review pairs gives bland, averaged reviews. Longer training makes them more generic, and they miss much of the range of concerns human reviewers raise. To fix this, the authors propose REVIEWER2, a two-stage system:
- one fine-tuned model reads the paper and proposes aspect prompts, meaning the points a review should address;
- a second model writes a review for the paper conditioned on one such prompt.

Both are built on LongLoRA, so whole papers fit into a 32k-token context instead of extractive summaries. Existing corpora lack aspect prompts, so the authors created them with PGE. This pipeline derives a prompt from each human review and keeps it only after a self-evaluation check. The released dataset covers 27k papers and 99k reviews. In experiments across venues, REVIEWER2 produces more specific reviews that better span human viewpoints than single-stage baselines, and authors can steer it toward chosen aspects.

## Key points
- **Dataset:** about 27k papers and 99k reviews from six venues (ICLR, NeurIPS, ACL, ARR, COLING, CONLL), annotated with aspect prompts.
  - NeurIPS and ICLR reviews come from fresh crawls.
  - Other material comes from PeerRead and NLPeer.
- **PGE pipeline:**
  - Llama-2-70B-Chat writes a prompt from each review and then scores it on a 5-point scale.
  - Any prompt scoring below 5 is regenerated.
  - Only reviews, not papers, are given as input, because the model's context is limited to 4,096 tokens.
- **Long-context training:** uses LoRA+ (with trainable embedding and normalization layers) and S2-Attn. Average paper length is 6,229 tokens.
- **Specificity:** single-stage baselines (SINGLE S, SINGLE S-E) become more generic with more training steps. The prompt-based variants become more specific as training continues.
- **Coverability (lower is better; 0 matches human diversity):** full-context REVIEWER2 scores 2.91–5.09 across venues. The extracted-context REVIEWER2-E scores 12.66–16.62.

*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

- [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) — University, Ithaca, United States · 120 works · 59,940 citations

📚 Shelves (5): [🖥️ 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 · [🎭 History and Philosophy of Science](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/history-and-philosophy-of-science/) · 53 works

## Cite

Cite as: Zhaolin Gao, Kiante Brantley and Thorsten Joachims. 2024. Reviewer2: Optimizing Review Generation Through Prompt Generation. arXiv:2402.10886.

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

```bibtex
@misc{gao2024reviewer2,
  title = {{Reviewer2: Optimizing Review Generation Through Prompt Generation}},
  author = {Zhaolin Gao, Kiante Brantley and Thorsten Joachims},
  year = {2024},
  doi = {10.48550/arxiv.2402.10886},
  eprint = {2402.10886},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2402.10886}
}
```

- [← previous MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response](https://md.research.elamur.ai/free/en/papers/deng-2024-musilingo-bridging-music-text-pre/)
- [next → Sailor: Open Language Models for South-East Asia](https://md.research.elamur.ai/free/en/papers/dou-2024-sailor-open-language-models-south/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/7/)

## References

45 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adrian G Barnett, Jolieke C van der Pols, and Annette J Dobson. 2004. Regression to the mean: what it is and how to deal with it. International Journal of Epidemiology, 34(1):215–220. [find](https://scholar.google.com/scholar?q=Adrian+G+Barnett%2C+Jolieke+C+van+der+Pols%2C+and+Annette+J+Dobson%2E+2004%2E+Regression+to+the+mean%3A+what+it+is+and+how+to+deal+with+it%2E+International+Journal+of+Epidemiology%2C+34%281%29%3A215%E2%80%93220%2E)
2. Bo-Christer Björk and David Solomon. 2013. The publishing delay in scholarly peer-reviewed journals. Journal of Informetrics, 7(4):914–923. [find](https://scholar.google.com/scholar?q=Bo%2DChrister+Bj%C3%B6rk+and+David+Solomon%2E+2013%2E+The+publishing+delay+in+scholarly+peer%2Dreviewed+journals%2E+Journal+of+Informetrics%2C+7%284%29%3A914%E2%80%93923%2E)
3. Lutz Bornmann and Ruediger Mutz. 2014. Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references. Preprint, arXiv:1402.4578. — [arXiv:1402.4578](https://arxiv.org/abs/1402.4578) [find](https://scholar.google.com/scholar?q=Lutz+Bornmann+and+Ruediger+Mutz%2E+2014%2E+Growth+rates+of+modern+science%3A+A+bibliometric+analysis+based+on+the+number+of+publications+and+cited+references%2E+Preprint%2C+arXiv%3A1402%2E4578%2E+%E2%80%94+%5BarXiv%3A1402%2E4578%5D%28)
4. Yen-Chun Chen and Mohit Bansal. 2018. [Fast abstractive summarization with reinforce-selected sentence rewriting](https://md.research.elamur.ai/free/en/papers/chen-2018-fast-abstractive-summarization-reinforce-selected/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 675–686, Melbourne, Australia. Association for Computational Ling…
5. Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, and Jiaya Jia. 2023. [Longlora: Efficient fine-tuning of long-context large language models](https://md.research.elamur.ai/free/en/papers/chen-2023-longlora-efficient-fine-tuning-long/). Preprint, arXiv:2309.12307.
6. Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. 2020. [Specter: Document-level representation learning using citation-informed transformers](https://md.research.elamur.ai/free/en/papers/cohan-2020-specter-document-level-representation-learning/). Preprint, arXiv:2004.07180.
7. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, Lei Li, and Zhifang Sui. 2023. [A survey on in-context learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/). Preprint, arXiv:2301.00234.
8. Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi, Zhengbao Jiang, and Graham Neubig. 2021. [GSum: A general framework for guided neural abstractive summarization](https://md.research.elamur.ai/free/en/papers/dou-2021-gsum-general-framework-guided-neural/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
9. Nils Dycke, Ilia Kuznetsov, and Iryna Gurevych. 2023. [NLPeer: A unified resource for the computational study of peer review](https://md.research.elamur.ai/free/en/papers/dycke-2023-nlpeer-unified-resource-computational-study/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5049– 5073, Toronto, Canada. Association for Computat…
10. Tomáš Foltýnek, Norman Meuschke, and Bela Gipp. 2019. Academic plagiarism detection: A systematic literature review. ACM Comput. Surv., 52(6). [find](https://scholar.google.com/scholar?q=Tom%C3%A1%C5%A1+Folt%C3%BDnek%2C+Norman+Meuschke%2C+and+Bela+Gipp%2E+2019%2E+Academic+plagiarism+detection%3A+A+systematic+literature+review%2E+ACM+Comput%2E+Surv%2E%2C+52%286%29%2E)
11. Sebastian Gehrmann, Yuntian Deng, and Alexander M. Rush. 2018. [Bottom-up abstractive summarization](https://md.research.elamur.ai/free/en/papers/gehrmann-2018-bottom-up-abstractive-summarization/). Preprint, arXiv:1808.10792.
12. Tirthankar Ghosal, Ravi Sonam, Asif Ekbal, Sriparna Saha, and Pushpak Bhattacharyya. 2019. Is the paper within scope? are you fishing in the right pond? [find](https://scholar.google.com/scholar?q=Tirthankar+Ghosal%2C+Ravi+Sonam%2C+Asif+Ekbal%2C+Sriparna+Saha%2C+and+Pushpak+Bhattacharyya%2E+2019%2E+Is+the+paper+within+scope%3F+are+you+fishing+in+the+right+pond%3F)
13. In 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL), pages 237–240. [find](https://scholar.google.com/scholar?q=In+2019+ACM%2FIEEE+Joint+Conference+on+Digital+Libraries+%28JCDL%29%2C+pages+237%E2%80%93240%2E)
14. Or Honovich, Thomas Scialom, Omer Levy, and Timo Schick. 2022. [Unnatural instructions: Tuning language models with (almost) no human labor](https://md.research.elamur.ai/free/en/papers/honovich-2023-unnatural-instructions-tuning-language-models/). Preprint, arXiv:2212.09689.
15. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). Preprint, arXiv:2106.09685.
16. Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, and Roy Schwartz. 2018a. [A dataset of peer reviews (PeerRead): Collection, insights and NLP applications](https://md.research.elamur.ai/free/en/papers/kang-2018-dataset-peer-reviews-peerread-collection/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Com…
17. Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, and Roy Schwartz. 2018b. [A dataset of peer reviews (peerread): Collection, insights and nlp applications](https://md.research.elamur.ai/free/en/papers/kang-2018-dataset-peer-reviews-peerread-collection/). Preprint, arXiv:1804.09635.
18. Jacalyn Kelly, Tara Sadeghieh, and Khosrow Adeli. 2014. Peer review in scientific publications: Benefits, critiques, & a survival guide. EJIFCC, page 227–243. [find](https://scholar.google.com/scholar?q=Jacalyn+Kelly%2C+Tara+Sadeghieh%2C+and+Khosrow+Adeli%2E+2014%2E+Peer+review+in+scientific+publications%3A+Benefits%2C+critiques%2C+%26+a+survival+guide%2E+EJIFCC%2C+page+227%E2%80%93243%2E)
19. Ari Kobren, Barna Saha, and Andrew McCallum. 2019. Paper matching with local fairness constraints. Preprint, arXiv:1905.11924. — [arXiv:1905.11924](https://arxiv.org/abs/1905.11924) [find](https://scholar.google.com/scholar?q=Ari+Kobren%2C+Barna+Saha%2C+and+Andrew+McCallum%2E+2019%2E+Paper+matching+with+local+fairness+constraints%2E+Preprint%2C+arXiv%3A1905%2E11924%2E+%E2%80%94+%5BarXiv%3A1905%2E11924%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1905%2E11924%29)
20. Diego Kozlowski, Vincent Larivière, Cassidy R. Sugimoto, and Thema Monroe-White. 2022. Intersectional inequalities in science. Proceedings of the National Academy of Sciences, 119(2):e2113067119. [find](https://scholar.google.com/scholar?q=Diego+Kozlowski%2C+Vincent+Larivi%C3%A8re%2C+Cassidy+R%2E+Sugimoto%2C+and+Thema+Monroe%2DWhite%2E+2022%2E+Intersectional+inequalities+in+science%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+119%282%29%3Ae2113067119%2E)
21. Carole J. Lee, Cassidy R. Sugimoto, Guo Zhang, and Blaise Cronin. 2012. Bias in peer review. ASIS&T. [find](https://scholar.google.com/scholar?q=Carole+J%2E+Lee%2C+Cassidy+R%2E+Sugimoto%2C+Guo+Zhang%2C+and+Blaise+Cronin%2E+2012%2E+Bias+in+peer+review%2E+ASIS%26T%2E)
22. Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Luke Zettlemoyer, Omer Levy, Jason Weston, and Mike Lewis. 2023. [Self-alignment with instruction back-translation](https://md.research.elamur.ai/free/en/papers/li-2023-self-alignment-instruction-backtranslation/). Preprint, arXiv:2308.06259.
23. Weixin Liang, Yuhui Zhang, Hancheng Cao, Binglu Wang, Daisy Ding, Xinyu Yang, Kailas Vodrahalli, Siyu He, Daniel Smith, Yian Yin, Daniel McFarland, and James Zou. 2023. Can large language models provide useful feedback on research papers? a large-scale empirical analysis. Preprint, arXiv:2310.01783. [find](https://scholar.google.com/scholar?q=Weixin+Liang%2C+Yuhui+Zhang%2C+Hancheng+Cao%2C+Binglu+Wang%2C+Daisy+Ding%2C+Xinyu+Yang%2C+Kailas+Vodrahalli%2C+Siyu+He%2C+Daniel+Smith%2C+Yian+Yin%2C+Daniel+McFarland%2C+and+James+Zou%2E+2023%2E+Can+large+language+models+provi)
24. Chin-Yew Lin and Eduard Hovy. 2003. [Automatic evaluation of summaries using n-gram co-occurrence statistics](https://md.research.elamur.ai/free/en/papers/lin-2003-automatic-evaluation-summaries-n-gram/). In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 150–157.
25. Jialiang Lin, Jiaxin Song, Zhangping Zhou, Yidong Chen, and Xiaodong Shi. 2023. Moprd: A multidisciplinary open peer review dataset. Neural Computing and Applications, 35(34):24191–24206. [find](https://scholar.google.com/scholar?q=Jialiang+Lin%2C+Jiaxin+Song%2C+Zhangping+Zhou%2C+Yidong+Chen%2C+and+Xiaodong+Shi%2E+2023%2E+Moprd%3A+A+multidisciplinary+open+peer+review+dataset%2E+Neural+Computing+and+Applications%2C+35%2834%29%3A24191%E2%80%9324206%2E)
26. Ryan Liu and Nihar B. Shah. 2023. Reviewergpt? an exploratory study on using large language models for paper reviewing. Preprint, arXiv:2306.00622. [find](https://scholar.google.com/scholar?q=Ryan+Liu+and+Nihar+B%2E+Shah%2E+2023%2E+Reviewergpt%3F+an+exploratory+study+on+using+large+language+models+for+paper+reviewing%2E+Preprint%2C+arXiv%3A2306%2E00622%2E)
27. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with… [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+Shashank+Gupta%2C+Bodhisattwa+Prasad+Majumder%2C+Katherine+Her)
28. Robert K. Merton. 1968. The matthew effect in science. Science, 159(3810):56–63. [find](https://scholar.google.com/scholar?q=Robert+K%2E+Merton%2E+1968%2E+The+matthew+effect+in+science%2E+Science%2C+159%283810%29%3A56%E2%80%9363%2E)
29. Mathias Wullum Nielsen and Jens Peter Andersen. 2021. Global citation inequality is on the rise. Proceedings of the National Academy of Sciences, 118(7):e2012208118. [find](https://scholar.google.com/scholar?q=Mathias+Wullum+Nielsen+and+Jens+Peter+Andersen%2E+2021%2E+Global+citation+inequality+is+on+the+rise%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+118%287%29%3Ae2012208118%2E)
30. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv:2303.08774.
31. Preprint, Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
32. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: A method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, page 311–318, USA. Association for Computational Linguistics.
33. Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’20, page 3505–3506,… [find](https://scholar.google.com/scholar?q=Jeff+Rasley%2C+Samyam+Rajbhandari%2C+Olatunji+Ruwase%2C+and+Yuxiong+He%2E+2020%2E+Deepspeed%3A+System+optimizations+enable+training+deep+learning+models+with+over+100+billion+parameters%2E+In+Proceedings+of+the+26t)
34. Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Da… — [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/)
35. Chenhui Shen, Liying Cheng, Ran Zhou, Lidong Bing, Yang You, and Luo Si. 2022. MReD: A meta-review dataset for structure-controllable text generation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2521–2535, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chenhui+Shen%2C+Liying+Cheng%2C+Ran+Zhou%2C+Lidong+Bing%2C+Yang+You%2C+and+Luo+Si%2E+2022%2E+MReD%3A+A+meta%2Dreview+dataset+for+structure%2Dcontrollable+text+generation%2E+In+Findings+of+the+Association+for+Computational+)
36. Ivan Stelmakh, Nihar B. Shah, and Aarti Singh. 2019. Peerreview4all: Fair and accurate reviewer assignment in peer review. Preprint, arXiv:1806.06237. — [arXiv:1806.06237](https://arxiv.org/abs/1806.06237) [find](https://scholar.google.com/scholar?q=Ivan+Stelmakh%2C+Nihar+B%2E+Shah%2C+and+Aarti+Singh%2E+2019%2E+Peerreview4all%3A+Fair+and+accurate+reviewer+assignment+in+peer+review%2E+Preprint%2C+arXiv%3A1806%2E06237%2E+%E2%80%94+%5BarXiv%3A1806%2E06237%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1806%2E0)
37. Zhiqing Sun, Yikang Shen, Qinhong Zhou, Hongxin Zhang, Zhenfang Chen, David Cox, Yiming Yang, and Chuang Gan. 2023. [Principle-driven self-alignment of language models from scratch with minimal human supervision](https://md.research.elamur.ai/free/en/papers/sun-2023-principle-driven-self-alignment-language/). Preprint, arXiv:2305.03047.
38. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
39. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research, 9(86):2579–2605. [find](https://scholar.google.com/scholar?q=Laurens+van+der+Maaten+and+Geoffrey+Hinton%2E+2008%2E+Visualizing+data+using+t%2Dsne%2E+Journal+of+Machine+Learning+Research%2C+9%2886%29%3A2579%E2%80%932605%2E)
40. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. Self-instruct: Aligning language models with self-generated instructions. Preprint, arXiv:2212.10560. [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Yeganeh+Kordi%2C+Swaroop+Mishra%2C+Alisa+Liu%2C+Noah+A%2E+Smith%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+Self%2Dinstruct%3A+Aligning+language+models+with+self%2Dgenerated+instructions%2E+Preprin)
41. Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). Preprint, arXiv:2109.01652.
42. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. [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/). Preprint, arXiv:2201.11903.
43. Wenting Xiong and Diane Litman. 2011. Automatically predicting peer-review helpfulness. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 502–507, Portland, Oregon, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wenting+Xiong+and+Diane+Litman%2E+2011%2E+Automatically+predicting+peer%2Dreview+helpfulness%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+Human+Language+Techn)
44. Weizhe Yuan, Pengfei Liu, and Graham Neubig. 2021. Can we automate scientific reviewing? Preprint, arXiv:2102.00176. [find](https://scholar.google.com/scholar?q=Weizhe+Yuan%2C+Pengfei+Liu%2C+and+Graham+Neubig%2E+2021%2E+Can+we+automate+scientific+reviewing%3F+Preprint%2C+arXiv%3A2102%2E00176%2E)
45. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. Preprint, arXiv:1904.09675. *Figure 6: Embedding visualization of the reviews from human, R EVIEWER 2, and S INGLE S. The eclipse represents the confidence interval wi… [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q%2E+Weinberger%2C+and+Yoav+Artzi%2E+2020%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+Preprint%2C+arXiv%3A1904%2E09675%2E+%2AFigure+6%3A+Embedding+visualization+of+t)

*Updated 30 October 2026*