Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example, controlling the length of the generation or the complexity of the language that gets chosen. Most existing work attempts to integrate users' control by conditioning LM generations on natural language prompts or discrete control signals, which are often brittle and hard to scale. In this work, we are interested in continuous control signals, ones that exist along a spectrum that can't easily be captured in a natural language prompt or via existing techniques in conditional generation. Through a case study in controlling the precise response-length of generations, we demonstrate how an LM can be finetuned to expect a control vector that is interpolated between a "low" and a "high" token embedding. Our method more reliably exerts response-length control than in-context learning methods or fine-tuning methods that represent the control signal as a discrete signal.

Arka Media Works, the makers of the movie Bahubali, has tied up with the Centre for Innovation and Entrepreneurship (CIE) at IIIT Hyderabad to set up Media-Tech Accelerator to promote startups working in media technologies. "Movie production in the country now leverages many of the latest technologies available globally," Shobu Yarlagadda, Co-Founder and Chief Executive Officer of of Arka Media Works, has said. "This accelerator will support Indian innovators and start-ups in creating new technology driven solutions for the media and entertainment sector. The possibilities are immense," he said. The accelerator will help the shortlisted start-ups to benefit from cutting-edge research work being done at the International Institute of Information Technology (IIIT-Hyderabad).

Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, their applicability in real-world use cases may be limited due to their vague inner working and decision logic. A post-hoc explanation method can approximate the behavior of a black-box AI model by extracting relationships between feature values and outcomes. In this paper, we introduce a post-hoc explanation method that utilizes confident itemsets to approximate the behavior of black-box classifiers for medical information extraction. Incorporating medical concepts and semantics into the explanation process, our explanator finds semantic relations between inputs and outputs in different parts of the decision space of a black-box classifier. The experimental results show that our explanation method can outperform perturbation and decision set based explanators in terms of fidelity and interpretability of explanations produced for predictions on a disease-treatment information extraction task.

Pruning and quantization are widely applied techniques for compressing deep neural networks, often driven by the resource constraints of deploying models to mobile phones or embedded devices (Esteva et al., 2017; Lane & Warden, 2018). To-date, discussion around the relative merits of different compression methods has centered on the tradeoff between level of compression and top-line metrics such as top-1 and top-5 accuracy (Blalock et al., 2020). Along this dimension, compression techniques are remarkably successful. It is possible to prune the majority of weights (Gale et al., 2019; Evci et al., 2019) or heavily quantize the bit representation (Jacob et al., 2017) with negligible decreases to test-set accuracy. However, recent work by Hooker et al. (2019a) has found that the minimal changes to top-line metrics obscure critical differences in generalization between pruned and non-pruned networks. The authors establish that pruning disproportionately impacts predictive performance on a small subset of the dataset. We build upon this work and focus on the implications of these findings for a dataset with sensitive protected attributes such as gender and age. Our work addresses the question: Does compression amplify existing algorithmic bias?