Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
60 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment (2402.08785v1)

Published 13 Feb 2024 in cs.CL

Abstract: Do current LLMs better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment. Specifically, we first propose a structured format verbalizer to unify all graph data into a universal code-like format, which can simply represent the graph without any external graph-specific encoders. Furthermore, a graph instruction tuning stage is introduced to guide LLMs in solving graph reasoning and generation tasks. Finally, we identify potential hallucination problems in graph tasks and sample negative instances for preference alignment, the target of which is to enhance the output's reliability of the model. Extensive experiments across multiple graph-centric tasks exhibit that InstructGraph can achieve the best performance and outperform GPT-4 and LLaMA2 by more than 13\% and 38\%, respectively.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (83)
  1. Xalign: Cross-lingual fact-to-text alignment and generation for low-resource languages. In Companion of The Web Conference 2022, Virtual Event / Lyon, France, April 25 - 29, 2022, pages 171–175. ACM.
  2. Training a helpful and harmless assistant with reinforcement learning from human feedback. CoRR, abs/2204.05862.
  3. Semantic parsing on freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1533–1544. ACL.
  4. Graph of thoughts: Solving elaborate problems with large language models. CoRR, abs/2308.09687.
  5. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-12, 2008, pages 1247–1250. ACM.
  6. Ralph Allan Bradley and Milton E Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324–345.
  7. Language models are few-shot learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  8. Graphllm: Boosting graph reasoning ability of large language model. CoRR, abs/2310.05845.
  9. Eventnarrative: A large-scale event-centric dataset for knowledge graph-to-text generation. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual.
  10. Flashattention: Fast and memory-efficient exact attention with io-awareness. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  11. On the origin of hallucinations in conversational models: Is it the datasets or the models? In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022, pages 5271–5285. Association for Computational Linguistics.
  12. Mol-instructions: A large-scale biomolecular instruction dataset for large language models. CoRR, abs/2306.08018.
  13. What makes good in-context demonstrations for code intelligence tasks with llms? In 38th IEEE/ACM International Conference on Automated Software Engineering, ASE 2023, Luxembourg, September 11-15, 2023, pages 761–773. IEEE.
  14. Creating training corpora for NLG micro-planners. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pages 179–188. Association for Computational Linguistics.
  15. Citeseer: An automatic citation indexing system. In Proceedings of the 3rd ACM International Conference on Digital Libraries, June 23-26, 1998, Pittsburgh, PA, USA, pages 89–98. ACM.
  16. Beyond I.I.D.: three levels of generalization for question answering on knowledge bases. In WWW ’21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pages 3477–3488. ACM / IW3C2.
  17. Instructie: A chinese instruction-based information extraction dataset. CoRR, abs/2305.11527.
  18. Gpt4graph: Can large language models understand graph structured data ? an empirical evaluation and benchmarking. CoRR, abs/2305.15066.
  19. Pive: Prompting with iterative verification improving graph-based generative capability of llms. CoRR, abs/2305.12392.
  20. Ruining He and Julian J. McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In Proceedings of the 25th International Conference on World Wide Web, WWW 2016, Montreal, Canada, April 11 - 15, 2016, pages 507–517. ACM.
  21. Measuring massive multitask language understanding. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net.
  22. Parameter-efficient transfer learning for NLP. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pages 2790–2799. PMLR.
  23. Lora: Low-rank adaptation of large language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  24. Open graph benchmark: Datasets for machine learning on graphs. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  25. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12):248:1–248:38.
  26. Structgpt: A general framework for large language model to reason over structured data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 9237–9251. Association for Computational Linguistics.
  27. Large language models on graphs: A comprehensive survey. CoRR, abs/2312.02783.
  28. Genwiki: A dataset of 1.3 million content-sharing text and graphs for unsupervised graph-to-text generation. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, pages 2398–2409. International Committee on Computational Linguistics.
  29. KG-GPT: A general framework for reasoning on knowledge graphs using large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 9410–9421. Association for Computational Linguistics.
  30. Evaluating the factual consistency of abstractive text summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 9332–9346. Association for Computational Linguistics.
  31. Factuality enhanced language models for open-ended text generation. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  32. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  33. Halueval: A large-scale hallucination evaluation benchmark for large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 6449–6464. Association for Computational Linguistics.
  34. Inference-time intervention: Eliciting truthful answers from a language model. CoRR, abs/2306.03341.
  35. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pages 4582–4597. Association for Computational Linguistics.
  36. Truthfulqa: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 3214–3252. Association for Computational Linguistics.
  37. Reasoning on graphs: Faithful and interpretable large language model reasoning. CoRR, abs/2310.01061.
  38. At which training stage does code data help llms reasoning? CoRR, abs/2309.16298.
  39. Interactive learning from policy-dependent human feedback. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, volume 70 of Proceedings of Machine Learning Research, pages 2285–2294. PMLR.
  40. Automating the construction of internet portals with machine learning. Inf. Retr., 3(2):127–163.
  41. Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 12076–12100. Association for Computational Linguistics.
  42. Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. CoRR, abs/2305.15852.
  43. OpenAI. 2023a. GPT-4 technical report. CoRR, abs/2303.08774.
  44. OpenAI. 2023b. GPT-4 technical report. CoRR, abs/2303.08774.
  45. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  46. Panupong Pasupat and Percy Liang. 2015. Compositional semantic parsing on semi-structured tables. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, pages 1470–1480. The Association for Computer Linguistics.
  47. Let your graph do the talking: Encoding structured data for llms. arXiv preprint arXiv:2402.05862.
  48. Disentangled representation learning with large language models for text-attributed graphs. CoRR, abs/2310.18152.
  49. Direct preference optimization: Your language model is secretly a reward model. CoRR, abs/2305.18290.
  50. Walid S. Saba. 2023. Stochastic llms do not understand language: Towards symbolic, explainable and ontologically based llms. In Conceptual Modeling - 42nd International Conference, ER 2023, Lisbon, Portugal, November 6-9, 2023, Proceedings, volume 14320 of Lecture Notes in Computer Science, pages 3–19. Springer.
  51. A decade of knowledge graphs in natural language processing: A survey. CoRR, abs/2210.00105.
  52. Collective classification in network data. AI Mag., 29(3):93–106.
  53. Trusting your evidence: Hallucinate less with context-aware decoding. CoRR, abs/2305.14739.
  54. Conceptnet 5.5: An open multilingual graph of general knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA, pages 4444–4451. AAAI Press.
  55. Contrastive learning reduces hallucination in conversations. In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023, pages 13618–13626. AAAI Press.
  56. Challenging big-bench tasks and whether chain-of-thought can solve them. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 13003–13051. Association for Computational Linguistics.
  57. Evaluating the factual consistency of large language models through news summarization. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 5220–5255. Association for Computational Linguistics.
  58. Graphgpt: Graph instruction tuning for large language models. CoRR, abs/2310.13023.
  59. Graph neural prompting with large language models. CoRR, abs/2309.15427.
  60. Llama: Open and efficient foundation language models. CoRR, abs/2302.13971.
  61. Llama 2: Open foundation and fine-tuned chat models. CoRR, abs/2307.09288.
  62. Offloading accelerator-intensive workloads in CPU-GPU heterogeneous processors. In 26th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2021, Vasteras, Sweden, September 7-10, 2021, pages 1–8. IEEE.
  63. Can language models solve graph problems in natural language? CoRR, abs/2305.10037.
  64. Knowledge prompting in pre-trained language model for natural language understanding. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 3164–3177. Association for Computational Linguistics.
  65. Boosting language models reasoning with chain-of-knowledge prompting. CoRR, abs/2306.06427.
  66. Instructuie: Multi-task instruction tuning for unified information extraction. CoRR, abs/2304.08085.
  67. Rethinking the evaluation for conversational recommendation in the era of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 10052–10065. Association for Computational Linguistics.
  68. KEPLER: A unified model for knowledge embedding and pre-trained language representation. Trans. Assoc. Comput. Linguistics, 9:176–194.
  69. Natural language generation and understanding of big code for ai-assisted programming: A review. Entropy, 25(6):888.
  70. Symbol-llm: Towards foundational symbol-centric interface for large language models. CoRR, abs/2311.09278.
  71. If LLM is the wizard, then code is the wand: A survey on how code empowers large language models to serve as intelligent agents. CoRR, abs/2401.00812.
  72. Natural language is all a graph needs. CoRR, abs/2308.07134.
  73. Interactive molecular discovery with natural language. CoRR, abs/2306.11976.
  74. Jiawei Zhang. 2023. Graph-toolformer: To empower llms with graph reasoning ability via prompt augmented by chatgpt. CoRR, abs/2304.11116.
  75. Greaselm: Graph reasoning enhanced language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  76. Siren’s song in the AI ocean: A survey on hallucination in large language models. CoRR, abs/2309.01219.
  77. Llm4dyg: Can large language models solve problems on dynamic graphs? CoRR, abs/2310.17110.
  78. GIMLET: A unified graph-text model for instruction-based molecule zero-shot learning. CoRR, abs/2306.13089.
  79. Graphtext: Graph reasoning in text space. CoRR, abs/2310.01089.
  80. A survey of large language models. CoRR, abs/2303.18223.
  81. Pytorch FSDP: experiences on scaling fully sharded data parallel. Proc. VLDB Endow., 16(12):3848–3860.
  82. Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization. CoRR, abs/2311.16839.
  83. An interpretable reasoning network for multi-relation question answering. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, pages 2010–2022. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Jianing Wang (50 papers)
  2. Junda Wu (35 papers)
  3. Yupeng Hou (33 papers)
  4. Yao Liu (116 papers)
  5. Ming Gao (95 papers)
  6. Julian McAuley (238 papers)
Citations (21)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets