Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Chain of Thought Prompting Elicits Knowledge Augmentation (2307.01640v1)

Published 4 Jul 2023 in cs.CL

Abstract: The knowledge-augmented deep learning paradigm refers to a paradigm in which domain knowledge is identified and integrated into deep models. Conventional methods typically employ task-specific approaches to gather external knowledge from various sources. In contrast, LLMs are extensively pre-trained and can serve as a comprehensive source of external knowledge. In this paper, we propose CoT-KA, a Chain-of-Thought-based method that augments knowledge for deep learning. CoT-KA avoids the need for additional knowledge retrieval or knowledge reasoning models, as required in conventional augmentation methods. Our results demonstrate that CoT-KA outperforms both pure CoT-based methods and the non-augmented method across the majority of eleven publicly available benchmarks for various reasoning tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250.
  2. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  3. Reading wikipedia to answer open-domain questions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1870–1879.
  4. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311.
  5. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168.
  6. Knowledge-augmented deep learning and its applications: A survey. arXiv preprint arXiv:2212.00017.
  7. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346–361.
  8. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543.
  9. Learning to solve arithmetic word problems with verb categorization. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 523–533, Doha, Qatar. Association for Computational Linguistics.
  10. Gautier Izacard and Edouard Grave. 2021. Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Online. Association for Computational Linguistics.
  11. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781.
  12. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT, pages 4171–4186.
  13. Large language models are zero-shot reasoners. arXiv preprint arXiv:2205.11916.
  14. Parsing algebraic word problems into equations. Transactions of the Association for Computational Linguistics, 3:585–597.
  15. Albert: A lite bert for self-supervised learning of language representations. In International Conference on Learning Representations.
  16. Program induction by rationale generation: Learning to solve and explain algebraic word problems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 158–167, Vancouver, Canada. Association for Computational Linguistics.
  17. Are nlp models really able to solve simple math word problems? In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2080–2094.
  18. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(140):1–67.
  19. Okapi at trec-3. Nist Special Publication Sp, 109:109.
  20. Subhro Roy and Dan Roth. 2015. Solving general arithmetic word problems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1743–1752.
  21. Atomic: An atlas of machine commonsense for if-then reasoning. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 3027–3035.
  22. Conceptnet 5.5: An open multilingual graph of general knowledge. In Thirty-first AAAI conference on artificial intelligence.
  23. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615.
  24. Commonsenseqa: A question answering challenge targeting commonsense knowledge. In Proceedings of NAACL-HLT, pages 4149–4158.
  25. Logic-driven context extension and data augmentation for logical reasoning of text. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1619–1629.
  26. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171.
  27. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903.
  28. Scalable zero-shot entity linking with dense entity retrieval. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6397–6407.
  29. Reclor: A reading comprehension dataset requiring logical reasoning. In International Conference on Learning Representations.
  30. Glm-dialog: Noise-tolerant pre-training for knowledge-grounded dialogue generation. arXiv preprint arXiv:2302.14401.
  31. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493.
  32. A survey of large language models. arXiv preprint arXiv:2303.18223.
Citations (25)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now