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

Attribute Controlled Dialogue Prompting (2307.05228v1)

Published 11 Jul 2023 in cs.CL and cs.LG

Abstract: Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained LLMs to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data samples within a task, neglecting the fact that inputs vary greatly in some tasks such as open-domain dialogue generation. In this paper, we present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Specifically, we generate prompts based on instance-level control code, rather than the conversation history, to explore their impact on controlled dialogue generation. Experiments on popular open-domain dialogue datasets, evaluated on both automated metrics and human evaluation, demonstrate that our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.

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 (36)
  1. Abhaya Agarwal and Alon Lavie. 2007. Meteor: An automatic metric for mt evaluation with high levels of correlation with human judgments. Proceedings of WMT-08.
  2. Pada: A prompt-based autoregressive approach for adaptation to unseen domains. arXiv preprint arXiv:2102.12206.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Control prefixes for text generation. arXiv preprint arXiv:2110.08329.
  5. Bert: Pre-training of deep bidirectional transformers for language understanding. In 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 4171–4186.
  6. George Doddington. 2002. Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In Proceedings of the second international conference on Human Language Technology Research, pages 138–145.
  7. Wanyu Du and Yangfeng Ji. 2021. Sidecontrol: Controlled open-domain dialogue generation via additive side networks. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2175–2194.
  8. Making pre-trained language models better few-shot learners. 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), pages 3816–3830.
  9. Response generation with context-aware prompt learning. arXiv preprint arXiv:2111.02643.
  10. Parameter-efficient transfer learning with diff pruning. 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), pages 4884–4896.
  11. Investigating evaluation of open-domain dialogue systems with human generated multiple references. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 379–391.
  12. Hyperprompt: Prompt-based task-conditioning of transformers. In International Conference on Machine Learning, pages 8678–8690. PMLR.
  13. Call for customized conversation: Customized conversation grounding persona and knowledge. arXiv preprint arXiv:2112.08619.
  14. How can we know what language models know? Transactions of the Association for Computational Linguistics, 8:423–438.
  15. Instance-aware prompt learning for language understanding and generation. arXiv preprint arXiv:2201.07126.
  16. The power of scale for parameter-efficient prompt tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3045–3059.
  17. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110–119.
  18. Acute-eval: Improved dialogue evaluation with optimized questions and multi-turn comparisons. arXiv preprint arXiv:1909.03087.
  19. 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 (Volume 1: Long Papers), pages 4582–4597.
  20. Dailydialog: A manually labelled multi-turn dialogue dataset.
  21. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
  22. P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 61–68, Dublin, Ireland. Association for Computational Linguistics.
  23. Gpt understands, too. arXiv preprint arXiv:2103.10385.
  24. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
  25. Controllable natural language generation with contrastive prefixes. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2912–2924.
  26. Guanghui Qin and Jason Eisner. 2021. Learning how to ask: Querying lms with mixtures of soft prompts. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5203–5212.
  27. Improving language understanding by generative pre-training.
  28. Recipes for building an open-domain chatbot. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 300–325.
  29. Timo Schick and Hinrich Schütze. 2021a. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 255–269.
  30. Timo Schick and Hinrich Schütze. 2021b. It’s not just size that matters: Small language models are also few-shot learners. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2339–2352.
  31. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4222–4235.
  32. Idpg: An instance-dependent prompt generation method. arXiv preprint arXiv:2204.04497.
  33. Tailor: A prompt-based approach to attribute-based controlled text generation. arXiv preprint arXiv:2204.13362.
  34. Generating informative and diverse conversational responses via adversarial information maximization. Advances in Neural Information Processing Systems, 31.
  35. Dialogpt: Large-scale generative pre-training for conversational response generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 270–278.
  36. Calibrate before use: Improving few-shot performance of language models. arXiv preprint arXiv:2102.09690.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Runcheng Liu (3 papers)
  2. Ahmad Rashid (24 papers)
  3. Ivan Kobyzev (23 papers)
  4. Mehdi Rezagholizadeh (78 papers)
  5. Pascal Poupart (80 papers)
Citations (2)
View on Semantic Scholar