Dian Yu, Kenji Sagae
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.
Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses. Even though these problems are crucial and prevalent, they are mostly manually identified by model designers through interactions. Recently, some research instructs crowdworkers to goad the bots into triggering such problems. However, humans leverage superficial clues such as hate speech, while leaving systematic problems undercover. In this paper, we propose two methods including reinforcement learning to automatically trigger a dialog model into generating problematic responses. We show the effect of our methods in exposing safety and contradiction issues with state-of-the-art dialog models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.06950")
get_code_for_paper("2109.06950")
have("2109.06950")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.06950.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.06950)
Connect an agent — have() is free.