Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
51 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

Augmenting LLMs with Knowledge: A survey on hallucination prevention (2309.16459v1)

Published 28 Sep 2023 in cs.CL, cs.AI, and cs.LG

Abstract: Large pre-trained LLMs have demonstrated their proficiency in storing factual knowledge within their parameters and achieving remarkable results when fine-tuned for downstream natural language processing tasks. Nonetheless, their capacity to access and manipulate knowledge with precision remains constrained, resulting in performance disparities on knowledge-intensive tasks when compared to task-specific architectures. Additionally, the challenges of providing provenance for model decisions and maintaining up-to-date world knowledge persist as open research frontiers. To address these limitations, the integration of pre-trained models with differentiable access mechanisms to explicit non-parametric memory emerges as a promising solution. This survey delves into the realm of LLMs (LMs) augmented with the ability to tap into external knowledge sources, including external knowledge bases and search engines. While adhering to the standard objective of predicting missing tokens, these augmented LMs leverage diverse, possibly non-parametric external modules to augment their contextual processing capabilities, departing from the conventional LLMing paradigm. Through an exploration of current advancements in augmenting LLMs with knowledge, this work concludes that this emerging research direction holds the potential to address prevalent issues in traditional LMs, such as hallucinations, un-grounded responses, and scalability challenges.

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 (43)
  1. M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. de Oliveira Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman, A. Ray, R. Puri, G. Krueger, M. Petrov, H. Khlaaf, G. Sastry, P. Mishkin, B. Chan, S. Gray, N. Ryder, M. Pavlov, A. Power, L. Kaiser, M. Bavarian, C. Winter, P. Tillet, F. P. Such, D. Cummings, M. Plappert, F. Chantzis, E. Barnes, A. Herbert-Voss, W. H. Guss, A. Nichol, A. Paino, N. Tezak, J. Tang, I. Babuschkin, S. Balaji, S. Jain, W. Saunders, C. Hesse, A. N. Carr, J. Leike, J. Achiam, V. Misra, E. Morikawa, A. Radford, M. Knight, M. Brundage, M. Murati, K. Mayer, P. Welinder, B. McGrew, D. Amodei, S. McCandlish, I. Sutskever, and W. Zaremba, “Evaluating large language models trained on code,” 2021.
  2. T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, “Language models are few-shot learners,” 2020.
  3. S. Welleck, I. Kulikov, S. Roller, E. Dinan, K. Cho, and J. Weston, “Neural text generation with unlikelihood training,” 2019.
  4. J. Hoffmann, S. Borgeaud, A. Mensch, E. Buchatskaya, T. Cai, E. Rutherford, D. de Las Casas, L. A. Hendricks, J. Welbl, A. Clark, T. Hennigan, E. Noland, K. Millican, G. van den Driessche, B. Damoc, A. Guy, S. Osindero, K. Simonyan, E. Elsen, J. W. Rae, O. Vinyals, and L. Sifre, “Training compute-optimal large language models,” 2022.
  5. T. Scialom, T. Chakrabarty, and S. Muresan, “Fine-tuned language models are continual learners,” 2022.
  6. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel et al., “Retrieval-augmented generation for knowledge-intensive nlp tasks,” Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020.
  7. G. Izacard and E. Grave, “Leveraging passage retrieval with generative models for open domain question answering,” 2021.
  8. S. Borgeaud, A. Mensch, J. Hoffmann, T. Cai, E. Rutherford, K. Millican, G. van den Driessche, J.-B. Lespiau, B. Damoc, A. Clark, D. de Las Casas, A. Guy, J. Menick, R. Ring, T. Hennigan, S. Huang, L. Maggiore, C. Jones, A. Cassirer, A. Brock, M. Paganini, G. Irving, O. Vinyals, S. Osindero, K. Simonyan, J. W. Rae, E. Elsen, and L. Sifre, “Improving language models by retrieving from trillions of tokens,” 2022.
  9. G. Izacard, P. Lewis, M. Lomeli, L. Hosseini, F. Petroni, T. Schick, J. Dwivedi-Yu, A. Joulin, S. Riedel, and E. Grave, “Atlas: Few-shot learning with retrieval augmented language models,” 2022.
  10. H. Sun, B. Dhingra, M. Zaheer, K. Mazaitis, R. Salakhutdinov, and W. Cohen, “Open domain question answering using early fusion of knowledge bases and text,” in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.   Brussels, Belgium: Association for Computational Linguistics, Oct.-Nov. 2018, pp. 4231–4242. [Online]. Available: https://aclanthology.org/D18-1455
  11. H. Sun, T. Bedrax-Weiss, and W. W. Cohen, “Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text,” 2019.
  12. R. Thoppilan, D. D. Freitas, J. Hall, N. Shazeer, A. Kulshreshtha, H.-T. Cheng, A. Jin, T. Bos, L. Baker, Y. Du, Y. Li, H. Lee, H. S. Zheng, A. Ghafouri, M. Menegali, Y. Huang, M. Krikun, D. Lepikhin, J. Qin, D. Chen, Y. Xu, Z. Chen, A. Roberts, M. Bosma, V. Zhao, Y. Zhou, C.-C. Chang, I. Krivokon, W. Rusch, M. Pickett, P. Srinivasan, L. Man, K. Meier-Hellstern, M. R. Morris, T. Doshi, R. D. Santos, T. Duke, J. Soraker, B. Zevenbergen, V. Prabhakaran, M. Diaz, B. Hutchinson, K. Olson, A. Molina, E. Hoffman-John, J. Lee, L. Aroyo, R. Rajakumar, A. Butryna, M. Lamm, V. Kuzmina, J. Fenton, A. Cohen, R. Bernstein, R. Kurzweil, B. Aguera-Arcas, C. Cui, M. Croak, E. Chi, and Q. Le, “Lamda: Language models for dialog applications,” 2022.
  13. M. Komeili, K. Shuster, and J. Weston, “Internet-augmented dialogue generation,” 2021.
  14. K. Shuster, M. Komeili, L. Adolphs, S. Roller, A. Szlam, and J. Weston, “Language models that seek for knowledge: Modular search and generation for dialogue and prompt completion,” 2022.
  15. Y. Bengio, R. Ducharme, and P. Vincent, “A neural probabilistic language model,” in Advances in Neural Information Processing Systems, T. Leen, T. Dietterich, and V. Tresp, Eds., vol. 13.   MIT Press, 2000. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2000/file/728f206c2a01bf572b5940d7d9a8fa4c-Paper.pdf
  16. D. P. Kingma and M. Welling, “An introduction to variational autoencoders,” Foundations and Trends® in Machine Learning, vol. 12, no. 4, pp. 307–392, 2019. [Online]. Available: https://doi.org/10.1561%2F2200000056
  17. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” 2014.
  18. A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, p. 9, 2019.
  19. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” 2023.
  20. I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” 2014.
  21. D. E. Rumelhart, G. E. Hinton, R. J. Williams et al., “Learning internal representations by error propagation,” 1985.
  22. M. I. Jordan, “Serial order: A parallel distributed processing approach,” in Advances in psychology.   Elsevier, 1997, vol. 121, pp. 471–495.
  23. Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, “Handwritten digit recognition with a back-propagation network,” Advances in neural information processing systems, vol. 2, 1989.
  24. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” 2019.
  25. C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-text transformer,” 2020.
  26. J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with gpus,” IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535–547, 2021.
  27. M. Schlichtkrull, T. N. Kipf, P. Bloem, R. Van Den Berg, I. Titov, and M. Welling, “Modeling relational data with graph convolutional networks,” in The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, Proceedings 15.   Springer, 2018, pp. 593–607.
  28. M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, and L. Zettlemoyer, “Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,” 2019.
  29. V. Karpukhin, B. Oğuz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W. tau Yih, “Dense passage retrieval for open-domain question answering,” 2020.
  30. K. Guu, K. Lee, Z. Tung, P. Pasupat, and M.-W. Chang, “Realm: Retrieval-augmented language model pre-training,” 2020.
  31. K. Lee, M.-W. Chang, and K. Toutanova, “Latent retrieval for weakly supervised open domain question answering,” 2019.
  32. G. Izacard, M. Caron, L. Hosseini, S. Riedel, P. Bojanowski, A. Joulin, and E. Grave, “Unsupervised dense information retrieval with contrastive learning,” 2022.
  33. R. Guo, P. Sun, E. Lindgren, Q. Geng, D. Simcha, F. Chern, and S. Kumar, “Accelerating large-scale inference with anisotropic vector quantization,” 2020.
  34. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 2017.
  35. Y. Li, D. Tarlow, M. Brockschmidt, and R. Zemel, “Gated graph sequence neural networks,” 2017.
  36. T. H. Haveliwala, “Topic-sensitive pagerank,” in Proceedings of the 11th International Conference on World Wide Web, ser. WWW ’02.   New York, NY, USA: Association for Computing Machinery, 2002, p. 517–526. [Online]. Available: https://doi.org/10.1145/511446.511513
  37. D. Chen, A. Fisch, J. Weston, and A. Bordes, “Reading wikipedia to answer open-domain questions,” 2017.
  38. A. S. Foundation. (2011) Apache lucene - scoring. Letzter Zugriff: 20. Oktober 2011. [Online]. Available: http://lucene.apache.org/java/3_4_0/scoring.html
  39. Microsoft, “Bing web search api,” 2023. [Online]. Available: https://www.microsoft.com/en-us/bing/apis/bing-web-search-api
  40. S. Roller, E. Dinan, N. Goyal, D. Ju, M. Williamson, Y. Liu, J. Xu, M. Ott, K. Shuster, E. M. Smith, Y.-L. Boureau, and J. Weston, “Recipes for building an open-domain chatbot,” 2020.
  41. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. L. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, J. Schulman, J. Hilton, F. Kelton, L. Miller, M. Simens, A. Askell, P. Welinder, P. Christiano, J. Leike, and R. Lowe, “Training language models to follow instructions with human feedback,” 2022.
  42. J. Xu, D. Ju, M. Li, Y.-L. Boureau, J. Weston, and E. Dinan, “Recipes for safety in open-domain chatbots,” 2021.
  43. E. Dinan, A. Fan, A. Williams, J. Urbanek, D. Kiela, and J. Weston, “Queens are powerful too: Mitigating gender bias in dialogue generation,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).   Online: Association for Computational Linguistics, Nov. 2020, pp. 8173–8188. [Online]. Available: https://aclanthology.org/2020.emnlp-main.656
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
Citations (15)
View on Semantic Scholar