Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning (2403.03102v4)

Published 5 Mar 2024 in cs.CL and cs.AI

Abstract: Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained LLMs to leverage dialogue history to characterize persona for completing personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Plato: Pre-trained dialogue generation model with discrete latent variable. arXiv preprint arXiv:1910.07931.
  2. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  3. Towards robust personalized dialogue generation via order-insensitive representation regularization. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7337–7345, Toronto, Canada. Association for Computational Linguistics.
  4. Towards robust personalized dialogue generation via order-insensitive representation regularization. arXiv preprint arXiv:2305.12782.
  5. Improving in-context few-shot learning via self-supervised training. arXiv preprint arXiv:2205.01703.
  6. Learning to memorize entailment and discourse relations for persona-consistent dialogues. arXiv preprint arXiv:2301.04871.
  7. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1–113.
  8. Cristian Danescu-Niculescu-Mizil and Lillian Lee. 2011. Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs. arXiv preprint arXiv:1106.3077.
  9. Edsger W Dijkstra. 2022. A note on two problems in connexion with graphs. In Edsger Wybe Dijkstra: His Life, Work, and Legacy, pages 287–290.
  10. The second conversational intelligence challenge (convai2). In The NeurIPS’18 Competition: From Machine Learning to Intelligent Conversations, pages 187–208. Springer.
  11. Cyclealign: Iterative distillation from black-box llm to white-box models for better human alignment.
  12. Personalized dialogue generation with persona-adaptive attention. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 12916–12923.
  13. Adam Tauman Kalai and Santosh S Vempala. 2023. Calibrated language models must hallucinate. arXiv preprint arXiv:2311.14648.
  14. We’ve had this conversation before: A novel approach to measuring dialog similarity. arXiv preprint arXiv:2110.05780.
  15. A diversity-promoting objective function for neural conversation models. arXiv preprint arXiv:1510.03055.
  16. Chin-Yew Lin and Franz Josef Och. 2004. Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pages 605–612.
  17. You impress me: Dialogue generation via mutual persona perception. arXiv preprint arXiv:2004.05388.
  18. Improving personality consistency in conversation by persona extending. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 1350–1359.
  19. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786.
  20. DialoGPS: Dialogue path sampling in continuous semantic space for data augmentation in multi-turn conversations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1267–1280, Toronto, Canada. Association for Computational Linguistics.
  21. One chatbot per person: Creating personalized chatbots based on implicit user profiles. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 555–564.
  22. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943.
  23. Training language models to follow instructions with human feedback.
  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. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22.
  26. Assigning personality/profile to a chatting machine for coherent conversation generation. In Ijcai, pages 4279–4285.
  27. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
  28. Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290.
  29. Preference ranking optimization for human alignment. arXiv preprint arXiv:2306.17492.
  30. Bob: Bert over bert for training persona-based dialogue models from limited personalized data. arXiv preprint arXiv:2106.06169.
  31. Profile consistency identification for open-domain dialogue agents. arXiv preprint arXiv:2009.09680.
  32. Exploiting persona information for diverse generation of conversational responses. arXiv preprint arXiv:1905.12188.
  33. Enhancing personalized dialogue generation with contrastive latent variables: Combining sparse and dense persona. arXiv preprint arXiv:2305.11482.
  34. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  35. MISC: A mixed strategy-aware model integrating COMET for emotional support conversation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 308–319, Dublin, Ireland. Association for Computational Linguistics.
  36. Learning to speak and act in a fantasy text adventure game. arXiv preprint arXiv:1903.03094.
  37. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
  38. Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149.
  39. Wizardlm: Empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244.
  40. RRHF: Rank responses to align language models with human feedback. In Thirty-seventh Conference on Neural Information Processing Systems.
  41. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243.
  42. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. arXiv preprint arXiv:1703.10960.
  43. Calibrate before use: Improving few-shot performance of language models. In International Conference on Machine Learning, pages 12697–12706. PMLR.
  44. A pre-training based personalized dialogue generation model with persona-sparse data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 9693–9700.
  45. Less is more: Learning to refine dialogue history for personalized dialogue generation. arXiv preprint arXiv:2204.08128.
  46. Paed: Zero-shot persona attribute extraction in dialogues. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9771–9787.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Chuanqi Cheng (6 papers)
  2. Quan Tu (16 papers)
  3. Wei Wu (482 papers)
  4. Shuo Shang (30 papers)
  5. Cunli Mao (4 papers)
  6. Zhengtao Yu (31 papers)
  7. Rui Yan (250 papers)

Summary

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

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