Controllable Mixed-Initiative Dialogue Generation through Prompting (2023.acl-short)
Copied to clipboard
| Challenge: | Mixed initiative dialogue systems allow all interacting agents to initiate actions to control the interaction. |
| Approach: | They propose to prompt large language models as a drop-in replacement for fine-tuning on conditional generation. |
| Outcome: | The proposed prompts improve fine-tuning and ground truth responses . the results show that generated responses are high . |
Similar Papers
Mix-Initiative Response Generation with Dynamic Prefix Tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing dialogue systems focus on training a holistic response generation model without any distinction between different initiatives. |
| Approach: | They propose a general mix-Initiative Dynamic Prefix Tuning framework to decouple different initiatives from the generation model. |
| Outcome: | The proposed framework outperforms baselines on two public dialogue datasets on human evaluations and automatic metrics. |
PLACES: Prompting Language Models for Social Conversation Synthesis (2023.findings-eacl)
Copied to clipboard
Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Seokhwan Kim, Andy Rosenbaum, Yang Liu, Zhou Yu, Dilek Hakkani-Tur
| Challenge: | Currently, collecting high quality conversational data is expensive and infeasible for many applications . a promising direction is to generate synthetic dialogues by prompting large language models . |
| Approach: | They propose to use expert-written conversations as in-context examples to generate synthetic dialogues by prompting large language models. |
| Outcome: | The proposed approach is generalizable to multi-party conversations, compared to human-collected conversations. |
Attribute Controlled Dialogue Prompting (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-tuning is an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. |
| Approach: | They propose an instance-specific prompt-tuning algorithm for dialog generation that generates prompts based on instance-level control code rather than the conversation history. |
| Outcome: | The proposed prompt-tuning module is a fraction of the size of the pretrained language model and saves memory and expensive storage space. |
Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies show that large pre-trained language models can be adapted to task-oriented dialog systems. |
| Approach: | They propose to use contextual dynamic prompting to generate prompts in dialogs . they propose to distill useful prompting signals from dialog contexts based on contextual dynamic . |
| Outcome: | The proposed approach improves response generation by 3 points and 17 points when dialog states are incorporated. |
Controllable Conversation Generation with Conversation Structures via Diffusion Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Current generation models fail to effectively utilize rich linguistic and world knowledge to generate coherent long text. |
| Approach: | They propose a conversation generation framework that incorporates human knowledge and conversation structures with both controllability and interpretability for better conversation generation. |
| Outcome: | The proposed framework incorporates human knowledge and conversation structures with both controllability and interpretability for better conversation generation. |
Fine-Grained Controllable Text Generation Using Non-Residual Prompting (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to control the text generation process are not expressive enough. |
| Approach: | They propose an encoder-decoder architecture that enables intermediate text prompts at arbitrary time steps. |
| Outcome: | The proposed architecture is expressive and versatile on multiple experimental settings. |
Plug-and-Play Conversational Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large conversational models that generate coherent and fluent responses often require large dialogue datasets. |
| Approach: | They propose and evaluate plug-and-play methods for controllable response generation . they demonstrate a high degree of control over the generated conversational responses . |
| Outcome: | The proposed method does not require further computation at decoding time and does not need fine-tuning of a large language model. |
Long-term Control for Dialogue Generation: Methods and Evaluation (2022.naacl-main)
Copied to clipboard
| Challenge: | Current approaches for controlling dialogue response generation focus on high-level attributes like style, sentiment, or topic. |
| Approach: | They propose a method that allows for more fine-grained control of dialogue response generation . they propose utterances that encourage the generation of control words in the future . |
| Outcome: | The proposed method outperforms state-of-the-art constrained generation baselines on task-oriented dialogue datasets and shows that it is more fine-grained than previous methods. |
Discourse-Aware Soft Prompting for Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in pre-trained langauge models (PLMs) have made great impact on text generation research. |
| Approach: | They propose to use hierarchical blocking to simulate a higher-level discourse structure of human written text and attention sparsity to learn sparse transformations on the softmax-function. |
| Outcome: | The proposed methods perform better on some generation tasks but don't generalize across all generation tasks. |
An Adaptive Prompt Generation Framework for Task-oriented Dialogue System (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing black-box large language models (LLMs) have excellent performance in task-oriented dialogue (TOD) tasks, but obtaining suitable prompts for specific tasks is challenging. |
| Approach: | They propose a black-box large language model that generates domain and slot information in the belief state, which serves as prior knowledge for subsequent prompt generation. |
| Outcome: | The proposed framework outperforms existing prompting methods on the MultiWOZ 2.0 dataset. |