---
title: "Talk like a Graph: Encoding Graphs for Large Language Models"
description: "Earlier work used only random graphs, so the authors release the GraphQA benchmark with more… 47 references, cited by 69 papers here."
authors: ["Bahare Fatemi", "Jonathan Halcrow", "Bryan Perozzi"]
year: 2023
venue: "arXiv:2310.04560"
source: "https://arxiv.org/abs/2310.04560"
doi: "10.48550/arxiv.2310.04560"
arxiv: "2310.04560"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/fatemi-2023-talk-like-graph-encoding-graphs/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/fatemi-2023-talk-like-graph-encoding-graphs/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/9/) / Talk like a Graph: Encoding Graphs for Large Language Models

# Talk like a Graph: Encoding Graphs for Large Language Models

**Authors:** [Bahare Fatemi](https://md.research.elamur.ai/free/en/authors/bahare-fatemi/), Jonathan Halcrow and [Bryan Perozzi](https://md.research.elamur.ai/free/en/authors/bryan-perozzi/) · **Year:** 2023 · **Venue:** arXiv:2310.04560 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2310.04560) · [PDF](https://arxiv.org/pdf/2310.04560) · [DOI 10.48550/arxiv.2310.04560](https://doi.org/10.48550/arxiv.2310.04560) · [arXiv 2310.04560](https://arxiv.org/abs/2310.04560) · [OpenAlex](https://openalex.org/W4387559176)

**Citations:** 12 citations (OpenAlex, 2026-10-14) · [69](https://md.research.elamur.ai/free/en/papers/fatemi-2023-talk-like-graph-encoding-graphs/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Large language models are increasingly asked to reason about relational data, but no one had systematically studied how to turn a graph into text for a frozen, black-box LLM. The authors frame this as choosing two functions, one that encodes the graph and one that rephrases the question, so that answer quality is maximized without access to model weights or gradients. They compare many textual encoders, ranging from plain edge lists and per-node neighbor lists to versions where nodes become people's names and edges become friendships or co-authorships. These are paired with standard prompting strategies and tested on basic tasks such as edge existence, node degree, counting nodes and edges, listing connected nodes, and cycle detection. Earlier work used only random graphs, so the authors release the GraphQA benchmark with more varied structures. They find that LLMs struggle even with simple graph questions, that the encoding choice shifts accuracy substantially, and that larger models reason better. The improvement from selecting an appropriate encoder varies across tasks, falling between 4.8% and 61.8%.

## Key points
- **Benchmark:** The paper introduces GraphQA. Earlier work relied on Erdős-Rényi (ER) graphs, following Wang et al. (2023). GraphQA adds more diverse and realistic graph structures.
- **Encoders:** Nine graph encoders are compared: Adjacency, Incident, Expert, Friendship, Co-authorship, Social network, Politician, GOT (Game of Thrones names) and SP (South Park names).
- **Prompting and models:** Five prompting heuristics are tested: ZERO-SHOT, FEW-SHOT, COT, ZERO-COT and COT-BAG. Iterative prompting was dropped after early trials because errors cascaded. The models are Flan-PaLM 2 XS, PaLM 2 S and PaLM 2 L.
- **Encoder results:** Encoders based on integer node IDs (Incident, Adjacency) are often strongest on structural tasks. On PaLM 2 L, Incident reaches up to 95.4% on node degree, and Adjacency reaches 100% on node count in the best settings. Name-based encoders sometimes score near zero on node degree.
- **Main findings:** LLMs perform poorly on basic graph tasks. The graph encoding function matters a great deal. Model capacity strongly affects graph reasoning. Choosing the right encoder yields gains of 4.8%–61.8%, depending on the task.

*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

- [Google](https://md.research.elamur.ai/free/en/companies/google/) — Company, Mountain View, United States · 492 works · 440,463 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Bahare Fatemi, Jonathan Halcrow and Bryan Perozzi. 2023. Talk like a Graph: Encoding Graphs for Large Language Models. arXiv:2310.04560.

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

```bibtex
@misc{fatemi2023talk,
  title = {{Talk like a Graph: Encoding Graphs for Large Language Models}},
  author = {Bahare Fatemi, Jonathan Halcrow and Bryan Perozzi},
  year = {2023},
  doi = {10.48550/arxiv.2310.04560},
  eprint = {2310.04560},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2310.04560}
}
```

- [← previous RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://md.research.elamur.ai/free/en/papers/pradeep-2023-rankvicuna-zero-shot-listwise-document/)
- [next → Large Language Models in Law: A Survey](https://md.research.elamur.ai/free/en/papers/lai-2023-large-language-models-law-survey/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/9/)

## References

47 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Oshin Agarwal, Heming Ge, Siamak Shakeri, and Rami Al-Rfou. [Knowledge graph based synthetic corpus generation for knowledge-enhanced language model pre-training](https://md.research.elamur.ai/free/en/papers/agarwal-2021-knowledge-graph-based-synthetic-corpus/), 2021.
2. Réka Albert and Albert-László Barabási. Statistical mechanics of complex networks. Reviews of modern physics, 74(1):47, 2002. [find](https://scholar.google.com/scholar?q=Re%CC%81ka+Albert+and+Albert%2DLa%CC%81szlo%CC%81+Baraba%CC%81si%2E+Statistical+mechanics+of+complex+networks%2E+Reviews+of+modern+physics%2C+74%281%29%3A47%2C+2002%2E)
3. Rohan Anil, Andrew M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al. [Palm 2 technical report](https://md.research.elamur.ai/free/en/papers/anil-2023-palm-2-technical-report/). arXiv preprint arXiv:2305.10403, 2023.
4. Albert-László Barabási and Réka Albert. Emergence of scaling in random networks. science, 286 (5439):509–512, 1999. [find](https://scholar.google.com/scholar?q=Albert%2DLa%CC%81szlo%CC%81+Baraba%CC%81si+and+Re%CC%81ka+Albert%2E+Emergence+of+scaling+in+random+networks%2E+science%2C+286+%285439%29%3A509%E2%80%93512%2C+1999%2E)
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901, 2020a.
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901, 2020b.
7. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. [Sparks of artificial general intelligence: Early experiments with gpt-4](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/). arXiv preprint arXiv:2303.12712, 2023.
8. Zhikai Chen, Haitao Mao, Hang Li, Wei Jin, Hongzhi Wen, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Wenqi Fan, Hui Liu, et al. Exploring the potential of large language models (llms) in learning on graphs. arXiv preprint arXiv:2307.03393, 2023. — [arXiv:2307.03393](https://arxiv.org/abs/2307.03393) [find](https://scholar.google.com/scholar?q=Zhikai+Chen%2C+Haitao+Mao%2C+Hang+Li%2C+Wei+Jin%2C+Hongzhi+Wen%2C+Xiaochi+Wei%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Wenqi+Fan%2C+Hui+Liu%2C+et+al%2E+Exploring+the+potential+of+large+language+models+%28llms%29+in+learning+on+graph)
9. 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/). arXiv preprint arXiv:2204.02311, 2022.
10. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416, 2022. [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Eric+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+et+al%2E+Scaling+instruction%2Dfinetuned+language+models%2E+arXiv+prep)
11. Peter Clark, Oyvind Tafjord, and Kyle Richardson. [Transformers as soft reasoners over language](https://md.research.elamur.ai/free/en/papers/clark-2020-transformers-soft-reasoners-over-language/). arXiv preprint arXiv:2002.05867, 2020.
12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805, 2018.
13. Vijay Prakash Dwivedi and Xavier Bresson. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699, 2020. — [arXiv:2012.09699](https://arxiv.org/abs/2012.09699) [find](https://scholar.google.com/scholar?q=Vijay+Prakash+Dwivedi+and+Xavier+Bresson%2E+A+generalization+of+transformer+networks+to+graphs%2E+arXiv+preprint+arXiv%3A2012%2E09699%2C+2020%2E+%E2%80%94+%5BarXiv%3A2012%2E09699%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2012%2E09699%29)
14. Paul Erdős and Alfred Rényi. On random graphs. Publicationes Mathematicae Debrecen, 6:290– 297, 1959. [find](https://scholar.google.com/scholar?q=Paul+Erdo%CC%8Bs+and+Alfred+Re%CC%81nyi%2E+On+random+graphs%2E+Publicationes+Mathematicae+Debrecen%2C+6%3A290%E2%80%93+297%2C+1959%2E)
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. Aric Hagberg, Pieter Swart, and Daniel S Chult. Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Lab.(LANL), Los Alamos, NM (United States), 2008. [find](https://scholar.google.com/scholar?q=Aric+Hagberg%2C+Pieter+Swart%2C+and+Daniel+S+Chult%2E+Exploring+network+structure%2C+dynamics%2C+and+function+using+networkx%2E+Technical+report%2C+Los+Alamos+National+Lab%2E%28LANL%29%2C+Los+Alamos%2C+NM+%28United+States%29%2C+20)
17. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). arXiv preprint arXiv:2103.03874, 2021.
18. Paul W Holland, Kathryn Blackmond Laskey, and Samuel Leinhardt. Stochastic blockmodels: First steps. Social networks, 5(2):109–137, 1983. [find](https://scholar.google.com/scholar?q=Paul+W+Holland%2C+Kathryn+Blackmond+Laskey%2C+and+Samuel+Leinhardt%2E+Stochastic+blockmodels%3A+First+steps%2E+Social+networks%2C+5%282%29%3A109%E2%80%93137%2C+1983%2E)
19. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). arXiv preprint arXiv:2106.09685, 2021.
20. Jie Huang and Kevin Chen-Chuan Chang. [Towards reasoning in large language models: A survey](https://md.research.elamur.ai/free/en/papers/huang-2023-reasoning-large-language-models-survey/). arXiv preprint arXiv:2212.10403, 2022.
21. Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, and Jiawei Han. Patton: Language model pretraining on text-rich networks. arXiv preprint arXiv:2305.12268, 2023. [find](https://scholar.google.com/scholar?q=Bowen+Jin%2C+Wentao+Zhang%2C+Yu+Zhang%2C+Yu+Meng%2C+Xinyang+Zhang%2C+Qi+Zhu%2C+and+Jiawei+Han%2E+Patton%3A+Language+model+pretraining+on+text%2Drich+networks%2E+arXiv+preprint+arXiv%3A2305%2E12268%2C+2023%2E)
22. Seyed Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, and Deepak Ramachandran. [Lambada: Backward chaining for automated reasoning in natural language](https://md.research.elamur.ai/free/en/papers/kazemi-2023-lambada-backward-chaining-automated-reasoning/). arXiv preprint arXiv:2212.13894, 2022.
23. Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. [Decomposed prompting: A modular approach for solving complex tasks](https://md.research.elamur.ai/free/en/papers/khot-2022-decomposed-prompting-modular-approach/). arXiv preprint arXiv:2210.02406, 2022.
24. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35:22199–22213, 2022.
25. Brian Lester, Rami Al-Rfou, and Noah Constant. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). arXiv preprint arXiv:2104.08691, 2021.
26. 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…
27. Jiachang Liu, Dinghan Shen, Yizhe Zhang, Bill Dolan, Lawrence Carin, and Weizhu Chen. [What makes good in-context examples for gpt-3?](https://md.research.elamur.ai/free/en/papers/liu-2022-what-makes-good-context-examples/) arXiv preprint arXiv:2101.06804, 2021.
28. Luis Müller, Mikhail Galkin, Christopher Morris, and Ladislav Rampášek. Attending to graph transformers. arXiv preprint arXiv:2302.04181, 2023. — [arXiv:2302.04181](https://arxiv.org/abs/2302.04181) [find](https://scholar.google.com/scholar?q=Luis+Mu%CC%88ller%2C+Mikhail+Galkin%2C+Christopher+Morris%2C+and+Ladislav+Rampa%CC%81s%CC%8Cek%2E+Attending+to+graph+transformers%2E+arXiv+preprint+arXiv%3A2302%2E04181%2C+2023%2E+%E2%80%94+%5BarXiv%3A2302%2E04181%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2302%2E04181)
29. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in Neural Information Processing Systems, 35: 27730–27744, 2022.
30. John Palowitch, Anton Tsitsulin, Brandon Mayer, and Bryan Perozzi. Graphworld: Fake graphs bring real insights for gnns. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3691–3701, 2022. [find](https://scholar.google.com/scholar?q=John+Palowitch%2C+Anton+Tsitsulin%2C+Brandon+Mayer%2C+and+Bryan+Perozzi%2E+Graphworld%3A+Fake+graphs+bring+real+insights+for+gnns%2E+In+Proceedings+of+the+28th+ACM+SIGKDD+Conference+on+Knowledge+Discovery+and+Dat)
31. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. [Unifying large language models and knowledge graphs: A roadmap](https://md.research.elamur.ai/free/en/papers/pan-2023-unifying-large-language-models-knowledge/), 2023.
32. Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. Automatic prompt optimization with” gradient descent” and beam search. arXiv preprint arXiv:2305.[03495, 2023](https://md.research.elamur.ai/free/en/papers/pryzant-2023-automatic-prompt-optimization-gradient-descent/).
33. Phillip Schneider, Tim Schopf, Juraj Vladika, Mikhail Galkin, Elena Simperl, and Florian Matthes. A decade of knowledge graphs in natural language processing: A survey. arXiv preprint arXiv:2210.00105, 2022. [find](https://scholar.google.com/scholar?q=Phillip+Schneider%2C+Tim+Schopf%2C+Juraj+Vladika%2C+Mikhail+Galkin%2C+Elena+Simperl%2C+and+Florian+Matthes%2E+A+decade+of+knowledge+graphs+in+natural+language+processing%3A+A+survey%2E+arXiv+preprint+arXiv%3A2210%2E00105)
34. Jianhao Shen, Yichun Yin, Lin Li, Lifeng Shang, Xin Jiang, Ming Zhang, and Qun Liu. Generate & rank: A multi-task framework for math word problems. arXiv preprint arXiv:2109.03034, 2021. [find](https://scholar.google.com/scholar?q=Jianhao+Shen%2C+Yichun+Yin%2C+Lin+Li%2C+Lifeng+Shang%2C+Xin+Jiang%2C+Ming+Zhang%2C+and+Qun+Liu%2E+Generate+%26+rank%3A+A+multi%2Dtask+framework+for+math+word+problems%2E+arXiv+preprint+arXiv%3A2109%2E03034%2C+2021%2E)
35. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30, 2017.
36. Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, and Yulia Tsvetkov. [Can language models solve graph problems in natural language?](https://md.research.elamur.ai/free/en/papers/wang-2023-language-models-solve-graph-problems/) arXiv preprint arXiv:2305.10037, 2023.
37. 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.
38. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. [Large language models as optimizers](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-optimizers/). arXiv preprint arXiv:2309.03409, 2023.
39. Mustafa Yasir, John Palowitch, Anton Tsitsulin, Long Tran-Thanh, and Bryan Perozzi. Examining the effects of degree distribution and homophily in graph learning models, 2023. [find](https://scholar.google.com/scholar?q=Mustafa+Yasir%2C+John+Palowitch%2C+Anton+Tsitsulin%2C+Long+Tran%2DThanh%2C+and+Bryan+Perozzi%2E+Examining+the+effects+of+degree+distribution+and+homophily+in+graph+learning+models%2C+2023%2E)
40. Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D Manning, Percy Liang, and Jure Leskovec. Deep bidirectional language-knowledge graph pretraining, 2022. [find](https://scholar.google.com/scholar?q=Michihiro+Yasunaga%2C+Antoine+Bosselut%2C+Hongyu+Ren%2C+Xikun+Zhang%2C+Christopher+D+Manning%2C+Percy+Liang%2C+and+Jure+Leskovec%2E+Deep+bidirectional+language%2Dknowledge+graph+pretraining%2C+2022%2E)
41. Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu, and Yongfeng Zhang. Natural language is all a graph needs. arXiv preprint arXiv:2308.07134, 2023. [find](https://scholar.google.com/scholar?q=Ruosong+Ye%2C+Caiqi+Zhang%2C+Runhui+Wang%2C+Shuyuan+Xu%2C+and+Yongfeng+Zhang%2E+Natural+language+is+all+a+graph+needs%2E+arXiv+preprint+arXiv%3A2308%2E07134%2C+2023%2E)
42. Jiawei Zhang, Haopeng Zhang, Congying Xia, and Li Sun. Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140, 2020. — [arXiv:2001.05140](https://arxiv.org/abs/2001.05140) [find](https://scholar.google.com/scholar?q=Jiawei+Zhang%2C+Haopeng+Zhang%2C+Congying+Xia%2C+and+Li+Sun%2E+Graph%2Dbert%3A+Only+attention+is+needed+for+learning+graph+representations%2E+arXiv+preprint+arXiv%3A2001%2E05140%2C+2020%2E+%E2%80%94+%5BarXiv%3A2001%2E05140%5D%28https%3A%2F%2Farxi)
43. Sarah J Zhang, Samuel Florin, Ariel N Lee, Eamon Niknafs, Andrei Marginean, Annie Wang, Keith Tyser, Zad Chin, Yann Hicke, Nikhil Singh, et al. Exploring the mit mathematics and eecs curriculum using large language models. arXiv preprint arXiv:2306.08997, 2023a. — [arXiv:2306.08997](https://arxiv.org/abs/2306.08997) [find](https://scholar.google.com/scholar?q=Sarah+J+Zhang%2C+Samuel+Florin%2C+Ariel+N+Lee%2C+Eamon+Niknafs%2C+Andrei+Marginean%2C+Annie+Wang%2C+Keith+Tyser%2C+Zad+Chin%2C+Yann+Hicke%2C+Nikhil+Singh%2C+et+al%2E+Exploring+the+mit+mathematics+and+eecs+curriculum+using+)
44. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, et al. Siren’s song in the ai ocean: A survey on hallucination in large language models. arXiv preprint arXiv:2309.[01219, 2023b](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/).
45. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223, 2023.
46. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, et al. [Least-to-most prompting enables complex reasoning in large language models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/). arXiv preprint arXiv:2205.10625, 2022a.
47. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. [Large language models are human-level prompt engineers](https://md.research.elamur.ai/free/en/papers/zhou-2022-large-language-models-human-level/). arXiv preprint arXiv:2211.01910, 2022b.

*Updated 2 November 2026*