Zhou Yu, Maximillian Chen, Weiyan Shi, Urvi Awasthi, Xiao Yu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. However, these supervised generation models are limited by the cost and quality of data annotation. We instead prompt large language models as a drop-in replacement to finetuning on conditional generation. We formalize prompt construction for controllable mixedinitiative dialogue. Our findings show improvements over fine-tuning and ground truth responses according to human evaluation and automatic metrics for two tasks: PersuasionFor-Good and Emotional Support Conversations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.04147")
get_code_for_paper("2305.04147")
have("2305.04147")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2305.04147.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2305.04147)
Connect an agent — have() is free.