Optimization problems involving mixed variables, i.e., variables of numerical and categorical nature, can be challenging to solve, especially in the presence of complex constraints. Moreover, when the objective function is the result of a complicated simulation or experiment, it may be expensive to evaluate. This paper proposes a novel surrogate-based global optimization algorithm to solve linearly constrained mixed-variable problems up to medium-large size (around 100 variables after encoding and 20 constraints) based on constructing a piecewise affine surrogate of the objective function over feasible samples. We introduce two types of exploration functions to efficiently search the feasible domain via mixed-integer linear programming solvers. We also provide a preference-based version of the algorithm, which can be used when only pairwise comparisons between samples can be acquired while the underlying objective function to minimize remains unquantified. The two algorithms are tested on mixed-variable benchmark problems with and without constraints. The results show that, within a small number of acquisitions, the proposed algorithms can often achieve better or comparable results than other existing methods.

Large language models (LLMs) can acquire strong code-generation capabilities through few-shot learning. In contrast, supervised fine-tuning is still needed for smaller models to achieve good performance. Such fine-tuning demands a large number of task-specific NL-code pairs, which are expensive to obtain. In this paper, we attempt to transfer the code generation ability of an LLM to a smaller model with the aid of weakly-supervised data. More specifically, we propose explicit knowledge transfer (EKT), which uses the few-shot capabilities of a teacher LLM to create NL-code pairs that we then filter for correctness and fine-tune the student on. We evaluate EKT on the task of generating code solutions to math word problems from the GSM8k dataset. We find that EKT not only yields better performance than training with expert iteration, but also outperforms knowledge distillation, another form of knowledge transfer. A GPT-Neo 1.3B model trained using EKT with a GPT-J teacher achieves a 12.4% pass@100 on GSM8k, while the same student and teacher trained with knowledge distillation yield only a 3.7% pass@100. We also show that it is possible for a student model to outperform the teacher using EKT.

Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining. The code used in the experiments are going to be made available at https://github.com/omidrohanian/bottleneck-adapters.

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize the underexplored task of translating saliency maps into natural language and compare methods that address two key challenges of this approach -- what and how to verbalize. In both automatic and human evaluation setups, using token-level attributions from text classification tasks, we compare two novel methods (search-based and instruction-based verbalizations) against conventional feature importance representations (heatmap visualizations and extractive rationales), measuring simulatability, faithfulness, helpfulness and ease of understanding. Instructing GPT-3.5 to generate saliency map verbalizations yields plausible explanations which include associations, abstractive summarization and commonsense reasoning, achieving by far the highest human ratings, but they are not faithfully capturing numeric information and are inconsistent in their interpretation of the task. In comparison, our search-based, model-free verbalization approach efficiently completes templated verbalizations, is faithful by design, but falls short in helpfulness and simulatability. Our results suggest that saliency map verbalization makes feature attribution explanations more comprehensible and less cognitively challenging to humans than conventional representations.

Autocomplete is a task where the user inputs a piece of text, termed prompt, which is conditioned by the model to generate semantically coherent continuation. Existing works for this task have primarily focused on datasets (e.g., email, chat) with high frequency user prompt patterns (or focused prompts) where word-based language models have been quite effective. In this work, we study the more challenging open-domain setting consisting of low frequency user prompt patterns (or broad prompts, e.g., prompt about 93rd academy awards) and demonstrate the effectiveness of character-based language models. We study this problem under memory-constrained settings (e.g., edge devices and smartphones), where character-based representation is effective in reducing the overall model size (in terms of parameters). We use WikiText-103 benchmark to simulate broad prompts and demonstrate that character models rival word models in exact match accuracy for the autocomplete task, when controlled for the model size. For instance, we show that a 20M parameter character model performs similar to an 80M parameter word model in the vanilla setting. We further propose novel methods to improve character models by incorporating inductive bias in the form of compositional information and representation transfer from large word models. Datasets and code used in this work are available at https://github.com/UBC-NLP/char_autocomplete.

It is often very challenging to manually design reward functions for complex, real-world tasks. To solve this, one can instead use reward learning to infer a reward function from data. However, there are often multiple reward functions that fit the data equally well, even in the infinite-data limit. This means that the reward function is only partially identifiable. In this work, we formally characterise the partial identifiability of the reward function given several popular reward learning data sources, including expert demonstrations and trajectory comparisons. We also analyse the impact of this partial identifiability for several downstream tasks, such as policy optimisation. We unify our results in a framework for comparing data sources and downstream tasks by their invariances, with implications for the design and selection of data sources for reward learning.

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer vision, it is impractical to directly apply them in natural language processing due to the discrete nature of the text. To address the problem, we propose a unified framework to extend the existing optimization-based adversarial attack methods in the vision domain to craft textual adversarial samples. In this framework, continuously optimized perturbations are added to the embedding layer and amplified in the forward propagation process. Then the final perturbed latent representations are decoded with a masked language model head to obtain potential adversarial samples. In this paper, we instantiate our framework with an attack algorithm named Textual Projected Gradient Descent (T-PGD). We find our algorithm effective even using proxy gradient information. Therefore, we perform the more challenging transfer black-box attack and conduct comprehensive experiments to evaluate our attack algorithm with several models on three benchmark datasets. Experimental results demonstrate that our method achieves overall better performance and produces more fluent and grammatical adversarial samples compared to strong baseline methods. The code and data are available at \url{https://github.com/Phantivia/T-PGD}.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Rapid advances in artificial intelligence (AI) such as Microsoft-backed OpenAI's ChatGPT are complicating governments' efforts to agree laws governing the use of the technology. The government is consulting Australia's main science advisory body and considering next steps, a spokesperson for the industry and science minister said in April. The Financial Conduct Authority, one of several state regulators that has been tasked with drawing up new guidelines covering AI, is consulting with the Alan Turing Institute and other legal and academic institutions to improve its understanding of the technology, a spokesperson told Reuters.

Tom Newhouse, vice president of Convergence Media, discusses the potential impact of artificial intelligence on elections after an RNC AI ad garnered attention. A bipartisan group of senators announced on Tuesday a series of briefings focused on artificial intelligence, including the first ever classified "All-Senators" briefing on the topic. "Dear Colleague: The advances we have seen in Artificial Intelligence (AI) in the last few months have been astounding. From helping the paralyzed walk again to allowing anyone to be a computer programmer, the technological breakthroughs are happening on almost a daily basis," Democratic Senate Majority Leader Chuck Schumer wrote in a letter to his fellow senators this week. "As AI transforms our world, the Senate must keep abreast of the extraordinary potential, and risks, AI presents."

Naftali Bennett spoke exclusively with Fox News Digital about the benefits of AI and the need to set parameters for its use now. The new drone swarm test conducted by the U.S. and its allies last week shows some of the wider applications of artificial intelligence (AI) in military settings while also raising some potential issues about how multiple militaries will be able to cooperate. "Just like coordination is needed to conduct classic, joint and coalition maneuvers and military operations, similar clear definitions of boundaries, tasks, responsibility and authority are needed to control and de-conflict drone swarms," retired Brig. Gen. Uri Engelhard, AI and cyber expert, member of the Israel Defense and Security Forum, told Fox News Digital. "If planned and conducted properly, the deployment of drone swarms should not be more challenging than other military activities."