In this work, we propose Table-LLM-Specialist, or Table-Specialist for short, as a new self-trained fine-tuning paradigm specifically designed for table tasks. Our insight is that for each table task, there often exist two dual versions of the same task, one generative and one classification in nature. Leveraging their duality, we propose a Generator-Validator paradigm, to iteratively generate-then-validate training data from language-models, to fine-tune stronger \sys models that can specialize in a given task, without requiring manually-labeled data. Our extensive evaluations suggest that our Table-Specialist has (1) \textit{strong performance} on diverse table tasks over vanilla language-models -- for example, Table-Specialist fine-tuned on GPT-3.5 not only outperforms vanilla GPT-3.5, but can often match or surpass GPT-4 level quality, (2) \textit{lower cost} to deploy, because when Table-Specialist fine-tuned on GPT-3.5 achieve GPT-4 level quality, it becomes possible to deploy smaller models with lower latency and inference cost, with comparable quality, and (3) \textit{better generalizability} when evaluated across multiple benchmarks, since \sys is fine-tuned on a broad range of training data systematically generated from diverse real tables. Our code and data will be available at https://github.com/microsoft/Table-LLM-Specialist.

Recent reports of emergency aircraft evacuations have highlighted an increasing tendency amongst evacuees to ignore clear safety warnings and to collect and carry personal items of baggage during egress. However, relatively little work has so far been done on quantifying the impact of such behaviour on the evacuation process. In this paper, we report the results of validated simulation experiments (using the Boeing 777 wide-body aircraft), which confirm that even a relatively low level of baggage collection can significantly delay evacuation. Our platform provides one possible framework for the investigation of processes and mitigation tactics to minimise the impact of baggage collection behaviour in future.

Around 60 years ago, the U.S. Department of Justice Civil Rights Division was established for prohibiting discrimination based on protected attributes. Over these 60 years, they established a set of policies and guidelines to identify and penalize those who discriminate1. The widespread use of machine learning (ML) models in routine life has prompted researchers to begin studying the extent to which these models are discriminatory. However, some researcher are unaware that the legal system already has well established procedures for describing and proving discrimination in law. In this series of blog posts, we'll try to bridge this gap.