4 papers · 1 filter
Uncertainty Quantification for Evaluating Machine Translation Bias
Ieva Raminta Staliūnaitė, Julius Cheng, Andreas Vlachos
The predictive uncertainty of machine translation (MT) models is typically used as a quality estimation proxy. In this work, we posit that apart from confidently translating when a…
Causal Estimation of Tokenisation Bias
Pietro Lesci, Clara Meister, Thomas Hofmann +2
Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps…
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
Liang Chen, Zekun Wang, Shuhuai Ren +24
Building on the foundations of language modeling in natural language processing, Next Token Prediction (NTP) has evolved into a versatile training objective for machine learning ta…
Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
Julius Cheng, Andreas Vlachos
Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accur…