SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.13887 · ACL · 2022

Probing the Robustness of Trained Metrics for Conversational Dialogue Systems

Jan Deriu, Mark Cieliebak, Von Däniken

arXiv · PDF · Open in the Atlas

Code that ran

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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained metrics. We apply our method to test recently proposed trained metrics. We find that they all are susceptible to giving high scores to responses generated by relatively simple and obviously flawed strategies that our method converges on. For instance, simply copying parts of the conversation context to form a response yields competitive scores or even outperforms responses written by humans.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2202.13887")
get_code_for_paper("2202.13887")
have("2202.13887")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2202.13887.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2202.13887.svg)](https://syntology.ai/paper/2202.13887)

Connect an agent — have() is free.