Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
91 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
o3 Pro
5 tokens/sec
GPT-4.1 Pro
15 tokens/sec
DeepSeek R1 via Azure Pro
33 tokens/sec
Gemini 2.5 Flash Deprecated
12 tokens/sec
2000 character limit reached

Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs (2401.04319v3)

Published 9 Jan 2024 in cs.CL and cs.AI

Abstract: In this paper, we explore a new way for user targeting, where non-expert marketers could select their target users solely given demands in natural language form. The key to this issue is how to transform natural languages into practical structured logical languages, i.e., the structured understanding of marketer demands. In practical scenarios, the demands of non-expert marketers are often abstract and diverse. Considering the impressive natural language processing ability of LLMs, we try to leverage LLMs to solve this issue. To stimulate the LLMs' reasoning ability, the chain-of-thought (CoT) prompting method is widely used, but existing methods still have some limitations in our scenario: (1) Previous methods either use simple "Let's think step by step" spells or provide fixed examples in demonstrations without considering compatibility between prompts and concrete questions, making LLMs ineffective when the marketers' demands are abstract and diverse. (2) Previous methods are often implemented in closed-source models or excessively large models, which is not suitable in industrial practical scenarios. Based on these, we propose ARALLM (i.e., Analogical Reasoning Augmented LLMs) consisting of two modules: Analogical Reasoning based Prompting and Reasoning-Augmented Multi-Task Model Distillation. Part of our data and code can be found at https://github.com/alipay/Analogic-Reasoning-Augmented-Large-Language-Model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Baichuan. 2023. Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305 (2023). https://arxiv.org/abs/2309.10305
  2. Paul E Black. 2004. Ratcliff/Obershelp pattern recognition. Dictionary of algorithms and data structures 17 (2004).
  3. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
  4. LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations. In 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). https://doi.org/10.18653/v1/2021.acl-long.198
  5. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 320–335.
  6. Dedre Gentner. 1983. Structure-mapping: A theoretical framework for analogy. Cognitive science 7, 2 (1983), 155–170.
  7. Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning. Proceedings of the ACM on Management of Data 1, 2 (2023), 1–28.
  8. hiyouga. 2023. LLaMA Factory. https://github.com/hiyouga/LLaMA-Factory.
  9. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. arXiv preprint arXiv:2305.02301 (2023).
  10. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021).
  11. Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing. Proceedings of the … AAAI Conference on Artificial Intelligence,Proceedings of the … AAAI Conference on Artificial Intelligence (May 2021).
  12. The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning. arXiv preprint arXiv:2305.14045 (2023).
  13. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022), 22199–22213.
  14. Vladimir I Levenshtein et al. 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, Vol. 10. Soviet Union, 707–710.
  15. A comprehensive evaluation of ChatGPT’s zero-shot Text-to-SQL capability. (Mar 2023).
  16. Audience expansion for online social network advertising. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 165–174.
  17. Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 5419–5431. https://aclanthology.org/2022.coling-1.481
  18. Score look-alike audiences. In 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW). IEEE, 647–654.
  19. A feature-pair-based associative classification approach to look-alike modeling for conversion-oriented user-targeting in tail campaigns. In Proceedings of the 20th international conference companion on World wide web. 85–86.
  20. Matt Post. 2018. A Call for Clarity in Reporting BLEU Scores. In Proceedings of the Third Conference on Machine Translation: Research Papers. Association for Computational Linguistics, Belgium, Brussels, 186–191. https://www.aclweb.org/anthology/W18-6319
  21. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv: Learning,arXiv: Learning (Oct 2019).
  22. Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633 (2021).
  23. Effective audience extension in online advertising. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2099–2108.
  24. Peter D Turney. 2008. The latent relation mapping engine: Algorithm and experiments. Journal of Artificial Intelligence Research 33 (2008), 615–655.
  25. RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.677
  26. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
  27. C-Pack: Packaged Resources To Advance General Chinese Embedding. arXiv:2309.07597 [cs.CL]
  28. Who Would be Interested in Services? An Entity Graph Learning System for User Targeting. arXiv preprint arXiv:2305.18780 (2023).
  29. Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation. arXiv:2305.15541 [cs.CL]
  30. Analogical inference enhanced knowledge graph embedding. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 4801–4808.
  31. Retrieve Anything To Augment Large Language Models. arXiv:2310.07554 [cs.IR]
  32. Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 4005–4013.
  33. Hubble: An industrial system for audience expansion in mobile marketing. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2455–2463.

Summary

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

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

Tweets