metric ID: mauve

Related Papers

RankGen: Improving Text Generation with Large Ranking Models

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractGiven an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also …...

31654

On the Efficacy of Sampling Adapters

Authors: nan

Publication: TIPSTER (2023)

DOI: nan

AbstractSampling-based decoding strategies are widely employed for generating text from probabilistic models, yet standard ancestral sampling often results in text that is degenerate or incoherent. To alleviate this issue, various …...

38776

Privacy-Preserving Domain Adaptation of Semantic Parsers

Authors: nan

Publication: TIPSTER (2023)

DOI: nan

AbstractTask-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can …...

38587