Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them.
13 PAPERS • 1 BENCHMARK
The Mafia Dataset was created to model the behavior of deceptive actors in the context of the Mafia game, as described in the paper “Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia”. We hope that this dataset will be of use to others studying the effects of deception on language use.
1 PAPER • NO BENCHMARKS YET