Ping Yu

TL;DR: This work presents a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions, not relying on distillation data, demonstrating highly effective self-alignment.

TL;DR: This work introduces Shepherd, a language model specifically tuned to critique responses and suggest refinements, extending beyond the capabilities of an untuned model to identify diverse errors and provide suggestions to remedy them.

TL;DR: The authors introduce ALERT, a benchmark and suite of analyses for assessing language models' reasoning ability comparing pre-trained and finetuned models on complex tasks that require reasoning skills to solve.

TL;DR: This paper investigated the role of explanations on different reasoning skills of large language models and found that having explanations in the few-shot exemplar has no significant impact on the model's performance when the model is finetuned, while positively affecting the non-finetuned counterpart.