Challenge: Existing methods to improve persona consistency on high-quality human-labeled persona datasets face high cost and poor scalability.
Approach: They propose a method to improve zero-shot persona consistency via in-context learning by pre-training a persona-augmented dialogue generation model and then using in-constant prompting mechanism to realize zero- shot persona customization.
Outcome: The proposed method improves persona consistency without compromising coherence and informativeness in zero-shot settings.

Similar Papers

“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to personalized dialogue generate pre-defined profiles that are time-consuming and labor-intensive to create.
Approach: They propose a framework that leverages dialogue history to characterize personas without pre-defined profiles.
Outcome: The proposed framework improves BLEU and ROUGE scores on three datasets and human evaluations further validate the proposed method.
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent work on dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs).
Approach: They propose a progressive zero-shot dataset generation framework which leverages feedback from the task-specific model to guide the generation of new training data via in-context examples.
Outcome: The proposed framework achieves on-par or superior performance with only 1% synthetic dataset size, when compared to baseline methods without in-context feedback.
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task.
Approach: They propose to use few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts.
Outcome: The proposed method outperforms the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.
PAED: Zero-Shot Persona Attribute Extraction in Dialogues (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for persona attribute extraction from conversations are inconsistent and unreliable.
Approach: They propose a model with a hard negative sampling strategy for generalized zero-shot persona attribute extraction.
Outcome: The proposed model outperforms existing models in persona attribute extraction tasks.
P5: Plug-and-Play Persona Prompting for Personalized Response Selection (2023.emnlp-main)

Copied to clipboard

Challenge: a plug-and-play persona prompting system can be used to generate personalized responses for real applications . a recent study shows that dialog context alone is insufficient for personalized response selection .
Approach: They propose a plug-and-play persona prompting method that can be used in real applications . they show that the method performs well in the zero-shot setting .
Outcome: The proposed method performs well in the zero-shot setting, and can be fine-tuned for even better performance.
Persona-Consistent Dialogue Generation via Pseudo Preference Tuning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for improving persona consistency in dialogues require external resources.
Approach: They propose a method for enhancing persona consistency in dialogue response generation using direct preference optimization using persona data.
Outcome: The proposed method produces more consistent and natural responses than previous methods.
Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (2023.findings-eacl)

Copied to clipboard

Challenge: Prompt-based methods with large pre-trained language models have shown impressive unaided performance across many NLP tasks.
Approach: They propose a meta-learning scheme to stabilize the ability of the model to perform well under various prompts and introduce a saliency model to limit dialogue text length.
Outcome: The proposed model improves on large pre-trained language models with labeled in-context exemplars and can be used to generate more exemplar queries.
Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement (2022.coling-1)

Copied to clipboard

Challenge: Existing methods suffer from incomprehensive persona tags that have unique and obscure meanings to describe human’s personality.
Approach: They propose a graph convolution network model with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph.
Outcome: The proposed model outperforms baselines by large margins and improves persona consistency in the generated responses.
Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension (2022.acl-short)

Copied to clipboard

Challenge: Existing models for dialogue comprehension are not available for the pre-training of such a model.
Approach: They propose a narrative-guided pre-training strategy that learns by narrating key information from a dialogue input.
Outcome: The proposed model performs better on four dialogue-based tasks and is comparable to existing models.
A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Copied to clipboard

Challenge: Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach: They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome: The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations