With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, as well as geographical and racial bias, among other biases. While existing works tackle this issue by preprocessing data and debiasing embeddings, the proposed methods require a lot of computational resources and annotation effort while being limited to certain types of biases. To address these issues, we introduce REFINE-LM, a debiasing method that uses reinforcement learning to handle different types of biases without any fine-tuning. By training a simple model on top of the word probability distribution of a LM, our bias agnostic reinforcement learning method enables model debiasing without human annotations or significant computational resources. Experiments conducted on a wide range of models, including several LMs, show that our method (i) significantly reduces stereotypical biases while preserving LMs performance; (ii) is applicable to different types of biases, generalizing across contexts such as gender, ethnicity, religion, and nationality-based biases; and (iii) it is not expensive to train.

'These bits of data shape a driver and can make him either a very good driver, a good driver, or a bad driver--it's just how you use it.'

ZhijiePan College of Computer Science and Technology Zhejiang University Hangzhou, China zhijie_pan@zju.edu.cn Abstract--Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers' behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety level of traffic system, we propose Driving Safety Credit inspired by credit score in financial security field, and design a scoring method using driver's trajectory data and violation records. First, we extract driving habits, aggressive driving behaviors and traffic violation behaviors from driver's trajectories and traffic violation records. Next, we train a classification modelto filtered out irrelevant features. And at last, we score each driver with selected features. We verify our proposed scoring method using 40 days of traffic simulation, and proves the effectiveness of our scoring method. I. INTRODUCTION Urban traffic worldwide is facing severe traffic safety problems.

The British Royal Air Force had a problem. It was 1943, and the Brits were using radar equipment to spot German submarines sneaking around off the western coast of France. The young men sitting in planes circling over the Bay of Biscay had more than enough motivation to keep a watchful eye for the telltale blips on the screens in front of them. Yet they had a worrying tendency to miss the signals they'd been trained to spot. The longer they spent looking at the screen, the less reliable they became.

The blind man that convinced Google to launch a self driving car firm: Steve Mahan revealed as first person to ride without a Google engineer on board (and he says it was'like driving with a very good driver') Firm says its cars have now driven three million miles on public roads Legally blind Steve Mahan was the person person allowed to drive solo Mahan said it was'like driving we a very good driver' Google today launched its car firm, to be called Waymo Mahan said it was'like driving we a very good driver' Steve Mahan, former director of the Santa Clara Valley Blind Center used one of Google's cars on his own in Austin in October 2015 - convincing the firm to spin out its project as car firm Waymo. Your left hand really DOES know what your right hand is... The'internet of the road': Government proposals call for... AirPods are FINALLY here after months of delays: Apple's... Your left hand really DOES know what your right hand is... The'internet of the road': Government proposals call for... AirPods are FINALLY here after months of delays: Apple's... The car Mahan rode in had a back up computers and multiple systems go control it.

A blind man has successfully traveled around Austin -- unaccompanied -- in a car without a steering wheel or floor pedals, Google announced Tuesday. After years of testing by Google engineers and employees, the company's new level of confidence in its fully autonomous technology was described as a milestone. "We've had almost driverless technology for a decade," said Google engineer Nathaniel Fairfield. "It's the hard parts of driving that really take the time and the effort to do right." Steve Mahan, who is legally blind, was the first non-Google employee to ride alone in the company's gumdrop-shaped autonomous car.