2000 character limit reached
"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Published 5 Mar 2024 in cs.CL and cs.AI | (2403.03102v4)
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.
- Plato: Pre-trained dialogue generation model with discrete latent variable. arXiv preprint arXiv:1910.07931.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
- 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.
- Towards robust personalized dialogue generation via order-insensitive representation regularization. arXiv preprint arXiv:2305.12782.
- Improving in-context few-shot learning via self-supervised training. arXiv preprint arXiv:2205.01703.
- Learning to memorize entailment and discourse relations for persona-consistent dialogues. arXiv preprint arXiv:2301.04871.
- Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1–113.
- 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.
- 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.
- The second conversational intelligence challenge (convai2). In The NeurIPS’18 Competition: From Machine Learning to Intelligent Conversations, pages 187–208. Springer.
- Cyclealign: Iterative distillation from black-box llm to white-box models for better human alignment.
- Personalized dialogue generation with persona-adaptive attention. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 12916–12923.
- Adam Tauman Kalai and Santosh S Vempala. 2023. Calibrated language models must hallucinate. arXiv preprint arXiv:2311.14648.
- We’ve had this conversation before: A novel approach to measuring dialog similarity. arXiv preprint arXiv:2110.05780.
- A diversity-promoting objective function for neural conversation models. arXiv preprint arXiv:1510.03055.
- 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.
- You impress me: Dialogue generation via mutual persona perception. arXiv preprint arXiv:2004.05388.
- Improving personality consistency in conversation by persona extending. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 1350–1359.
- Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. arXiv preprint arXiv:2104.08786.
- 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.
- 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.
- Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943.
- Training language models to follow instructions with human feedback.
- 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.
- Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22.
- Assigning personality/profile to a chatting machine for coherent conversation generation. In Ijcai, pages 4279–4285.
- Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
- Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290.
- Preference ranking optimization for human alignment. arXiv preprint arXiv:2306.17492.
- Bob: Bert over bert for training persona-based dialogue models from limited personalized data. arXiv preprint arXiv:2106.06169.
- Profile consistency identification for open-domain dialogue agents. arXiv preprint arXiv:2009.09680.
- Exploiting persona information for diverse generation of conversational responses. arXiv preprint arXiv:1905.12188.
- Enhancing personalized dialogue generation with contrastive latent variables: Combining sparse and dense persona. arXiv preprint arXiv:2305.11482.
- Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
- 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.
- Learning to speak and act in a fantasy text adventure game. arXiv preprint arXiv:1903.03094.
- Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
- Transfertransfo: A transfer learning approach for neural network based conversational agents. arXiv preprint arXiv:1901.08149.
- Wizardlm: Empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244.
- RRHF: Rank responses to align language models with human feedback. In Thirty-seventh Conference on Neural Information Processing Systems.
- Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243.
- Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. arXiv preprint arXiv:1703.10960.
- Calibrate before use: Improving few-shot performance of language models. In International Conference on Machine Learning, pages 12697–12706. PMLR.
- 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.
- Less is more: Learning to refine dialogue history for personalized dialogue generation. arXiv preprint arXiv:2204.08128.
- 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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.