In enhancing the reasoning capabilities of large language models (LLMs), prior research
primarily focuses on specific prompting techniques such as few-shot or zero-shot chain-of …

Given a language model (LM), maximum probability is a poor decoding objective for open-
ended generation, because it produces short and repetitive text. On the other hand …

We demonstrate the potential of few-shot translation systems, trained with unpaired
language data, for both high and low-resource language pairs. We show that with only 5 …

As major progress is made in open-ended text generation, measuring how close machine-
generated text is to human language remains a critical open problem. We introduce Mauve …

We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

Today's probabilistic language generators fall short when it comes to producing coherent
and fluent text despite the fact that the underlying models perform well under standard …

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT).
The community proposed specific network architectures and learning-based methods to …

Generative models of code, pretrained on large corpora of programs, have shown great
success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et …

Despite the progress in machine translation quality estimation and evaluation in the last
years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers …

Uncertainty estimation is important for ensuring safety and robustness of AI systems. While
most research in the area has focused on un-structured prediction tasks, limited work has …