Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A survey on fairness of large language models in e-commerce: progress, application, and challenge (2405.13025v2)

Published 15 May 2024 in cs.CL, cs.AI, and cs.CY

Abstract: This survey explores the fairness of LLMs in e-commerce, examining their progress, applications, and the challenges they face. LLMs have become pivotal in the e-commerce domain, offering innovative solutions and enhancing customer experiences. This work presents a comprehensive survey on the applications and challenges of LLMs in e-commerce. The paper begins by introducing the key principles underlying the use of LLMs in e-commerce, detailing the processes of pretraining, fine-tuning, and prompting that tailor these models to specific needs. It then explores the varied applications of LLMs in e-commerce, including product reviews, where they synthesize and analyze customer feedback; product recommendations, where they leverage consumer data to suggest relevant items; product information translation, enhancing global accessibility; and product question and answer sections, where they automate customer support. The paper critically addresses the fairness challenges in e-commerce, highlighting how biases in training data and algorithms can lead to unfair outcomes, such as reinforcing stereotypes or discriminating against certain groups. These issues not only undermine consumer trust, but also raise ethical and legal concerns. Finally, the work outlines future research directions, emphasizing the need for more equitable and transparent LLMs in e-commerce. It advocates for ongoing efforts to mitigate biases and improve the fairness of these systems, ensuring they serve diverse global markets effectively and ethically. Through this comprehensive analysis, the survey provides a holistic view of the current landscape of LLMs in e-commerce, offering insights into their potential and limitations, and guiding future endeavors in creating fairer and more inclusive e-commerce environments.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (85)
  1. Llama 2: Open foundation and fine-tuned chat models, 2023.
  2. OpenAI. Gpt-3: Language models are few-shot learners. arXiv preprint arXiv:2005.14165, 2021.
  3. Gpt-4 technical report, 2024.
  4. Anthropic. Claude’s constitution, May 2023.
  5. Anthropic. Model card and evaluations for claude models, July 2023.
  6. Ecomgpt: Instruction-tuning large language models with chain-of-task tasks for e-commerce, 2023.
  7. E-bert: Adapting bert to e-commerce with adaptive hybrid masking and neighbor product reconstruction. https://arxiv.org/pdf/2009.02835, 2021.
  8. Social biases in nlp models as barriers for persons with disabilities, 2020.
  9. Michal Měchura. A taxonomy of bias-causing ambiguities in machine translation. In Christian Hardmeier, Christine Basta, Marta R. Costa-jussà, Gabriel Stanovsky, and Hila Gonen, editors, Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 168–173, Seattle, Washington, July 2022. Association for Computational Linguistics.
  10. Albert: A lite bert for self-supervised learning of language representations. In Proceedings of the International Conference on Learning Representations (ICLR), 2020.
  11. Bert: Pre-training of deep bidirectional transformers for language understanding, 2019.
  12. Mike Lewis et al. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. ArXiv, abs/1910.13461, 2020.
  13. Electra: Pre-training text encoders as discriminators rather than generators. In International Conference on Learning Representations, 2020.
  14. Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems, volume 32, pages 5754–5764, 2019.
  15. Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223, 2019.
  16. Meta AI. Galactica: A large language model for science. ArXiv, abs/2211.12522, 2022.
  17. Language models are unsupervised multitask learners. OpenAI Blog, 1(8), 2019.
  18. Deberta: Decoding-enhanced bert with disentangled attention. In Proceedings of the AAAI Conference on Artificial Intelligence. AAAI, 2021.
  19. Meta AI. Llama: Open and efficient foundation models. ArXiv, abs/2302.13971, 2023.
  20. Tom B. Brown et al. Language models are few-shot learners. ArXiv, abs/2005.14165, 2020.
  21. Aakanksha Chowdhery et al. Palm: Scaling language modeling with pathways. ArXiv, abs/2204.02311, 2022.
  22. Stanford CRFM. Alpaca: A strong, replicable instruction-following model. Stanford Alpaca Project, 2023. Available at https://stanford-alpaca.gitbook.io/everything-you-need-to-know.
  23. Training language models to follow instructions with human feedback, 2022.
  24. Mixtral of experts, 2024.
  25. Kg-flip: Knowledge-guided fashion-domain language-image pre-training for e-commerce. In ACL 2023, 2023.
  26. General2specialized llms translation for e-commerce, 2024.
  27. ecellm: Generalizing large language models for e-commerce from large-scale, high-quality instruction data, 2024.
  28. Gpt4rec: A generative framework for personalized recommendation and user interests interpretation, 2023.
  29. MixPAVE: Mix-prompt tuning for few-shot product attribute value extraction. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, pages 9978–9991, Toronto, Canada, July 2023. Association for Computational Linguistics.
  30. Mave: A product dataset for multi-source attribute value extraction. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, WSDM ’22, page 1256–1265, New York, NY, USA, 2022. Association for Computing Machinery.
  31. Scaling up open tagging from tens to thousands: Comprehension empowered attribute value extraction from product title. In Anna Korhonen, David Traum, and Lluís Màrquez, editors, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5214–5223, Florence, Italy, July 2019. Association for Computational Linguistics.
  32. Continuous prompt tuning based textual entailment model for e-commerce entity typing, 2022.
  33. Prompt tuning large language models on personalized aspect extraction for recommendations, 2023.
  34. Enhancing collaborative filtering recommender with prompt-based sentiment analysis, 2022.
  35. A. Vaswani and et al. Attention is all you need. In Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017.
  36. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2022.
  37. Prefix-tuning: Optimizing continuous prompts for generation. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4582–4597, Online, August 2021. Association for Computational Linguistics.
  38. Full parameter fine-tuning for large language models with limited resources, 2023.
  39. Crosslingual generalization through multitask finetuning, 2023.
  40. Enhanced e-commerce attribute extraction: Innovating with decorative relation correction and llama 2.0-based annotation, 2023.
  41. Incorporating non-local information into information extraction systems by gibbs sampling. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL ’05, page 363–370, USA, 2005. Association for Computational Linguistics.
  42. Breaking the barrier: Utilizing large language models for industrial recommendation systems through an inferential knowledge graph, 2024.
  43. The power of scale for parameter-efficient prompt tuning, 2021.
  44. How transferable are features in deep neural networks? In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014.
  45. google-research-datasets/mave. https://github.com/google-research-datasets/MAVE.
  46. Gender bias and stereotypes in large language models. In Proceedings of The ACM Collective Intelligence Conference, CI ’23. ACM, November 2023.
  47. A survey on fairness in large language models, 2024.
  48. Unmasking and quantifying racial bias of large language models in medical report generation, 2024.
  49. A survey on popularity bias in recommender systems. https://arxiv.org/pdf/2308.01118.pdf, 2023. MediaFutures: Research Centre for Responsible Media Technology & Innovation, University of Bergen, Norway; AAU Klagenfurt, Austria.
  50. Seller-side outcome fairness in online marketplaces. https://arxiv.org/html/2312.03253v1, 2023.
  51. Evaluating the accuracy of implicit feedback from clicks and query reformulations in web search. ACM Transactions on Information Systems (TOIS), 25(2):7–es, 2007.
  52. Addressing seller-side fairness in recommender systems. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03):13805–13806, 2020.
  53. Aravind et al. Cikm. Beyond binary ratings: Debiasing recommender systems with exposure adjustment. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pages 2749–2758, 2021.
  54. Alleviating popularity bias in recommender systems: A multi-process fusion approach. Transactions on Emerging Telecommunications Technologies, page e4443, 2023.
  55. An end-to-end solution for named entity recognition in ecommerce search. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining, pages 1099–1107, 2023.
  56. Fixing the curse of the bad product descriptions: Search-boosted tag recommendation for e-commerce products. Information Processing & Management, 60(1):102912, 2023.
  57. Addressing marketing bias in product recommendations. https://nijianmo.github.io/paper/wsdm19.pdf, 2020.
  58. Alexa, in you, i trust! fairness and interpretability issues in e-commerce search through smart speakers. In Proceedings of the ACM Web Conference 2022, pages 3695–3705, 2022.
  59. Reasoning before comparison: Llm-enhanced semantic similarity metrics for domain specialized text analysis, 2024.
  60. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5), 2023.
  61. Recommendation system based on deep learning methods: a systematic review and new directions. Artificial Intelligence Review, 53:2709 – 2748, 2019.
  62. Zero-shot recommendation as language modeling, 2021.
  63. A survey on large language models for recommendation, 2023.
  64. A survey on the fairness of recommender systems. ACM Transactions on Information Systems, 41(3):1–43, February 2023.
  65. Semantic product search, 2019.
  66. Manipulating large language models to increase product visibility, 2024.
  67. Rethinking e-commerce search, 2023.
  68. Product attribute value extraction using large language models, 2024.
  69. No language left behind: Scaling human-centered machine translation, 2022.
  70. Multilingual denoising pre-training for neural machine translation, 2020.
  71. S. Liu and J. Liu. A survey of large language models. In Proceedings of the 2021 International Conference on Data Science and Business Analytics (DSBA 2021). ACM, 2021.
  72. Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners, 2024.
  73. Using large pretrained language models for answering user queries from product specifications, 2020.
  74. Conversational recommender system and large language model are made for each other in e-commerce pre-sales dialogue, 2023.
  75. Persistent anti-muslim bias in large language models, 2021.
  76. Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned, 2022.
  77. Exploring the filter bubble: The effect of using recommender systems on content diversity. In WWW 2014 - Proceedings of the 23rd International Conference on World Wide Web, WWW 2014 - Proceedings of the 23rd International Conference on World Wide Web, pages 677–686. Association for Computing Machinery, April 2014. 23rd International Conference on World Wide Web, WWW 2014 ; Conference date: 07-04-2014 Through 11-04-2014.
  78. Fairness in recommendation: Foundations, methods and applications, 2023.
  79. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183–186, April 2017.
  80. On measuring social biases in sentence encoders. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 622–628, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.
  81. Detecting emergent intersectional biases: Contextualized word embeddings contain a distribution of human-like biases. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’21. ACM, July 2021.
  82. Bold: Dataset and metrics for measuring biases in open-ended language generation. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21. ACM, March 2021.
  83. Reducing sentiment bias in language models via counterfactual evaluation. In Trevor Cohn, Yulan He, and Yang Liu, editors, Findings of the Association for Computational Linguistics: EMNLP 2020, pages 65–83, Online, November 2020. Association for Computational Linguistics.
  84. Wasserstein fair classification, 2019.
  85. Comprehensive evaluation of mal-api-2019 dataset by machine learning in malware detection. International Journal of Computer Science and Information Technology, 2(1):1–9, March 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Qingyang Ren (2 papers)
  2. Zilin Jiang (24 papers)
  3. Jinghan Cao (3 papers)
  4. Sijia Li (33 papers)
  5. Chiqu Li (1 paper)
  6. Yiyang Liu (12 papers)
  7. Shuning Huo (7 papers)
  8. Tiange He (1 paper)
  9. Yuan Chen (113 papers)
Citations (4)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets