Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in natural language. In SEO, we propose a stochastic validation method to ensure the update direction of experience, avoiding unavailing updates. Experimental results on three tasks for three LLMs demonstrate that experiences optimized by SEO can achieve consistently improved performance. Further analysis indicates that SEO-optimized experience can generalize to out-of-distribution data, boosting the performance of LLMs on similar tasks.

The metaphor studies community has developed numerous valuable labelled corpora in various languages over the years. Many of these resources are not only unknown to the NLP community, but are also often not easily shared among the researchers. Both in human sciences and in NLP, researchers could benefit from a centralised database of labelled resources, easily accessible and unified under an identical format. To facilitate this, we present MetaphorShare, a website to integrate metaphor datasets making them open and accessible. With this effort, our aim is to encourage researchers to share and upload more datasets in any language in order to facilitate metaphor studies and the development of future metaphor processing NLP systems. The website has four main functionalities: upload, download, search and label metaphor datasets. It is accessible at www.metaphorshare.com.

Large language models (LLMs) like ChatGPT and GPT-4 have attracted great attention given their surprising performance on a wide range of NLP tasks. Length controlled generation of LLMs emerges as an important topic, which enables users to fully leverage the capability of LLMs in more real-world scenarios like generating a proper answer or essay of a desired length. In addition, the autoregressive generation in LLMs is extremely time-consuming, while the ability of controlling this generated length can reduce the inference cost by limiting the length. Therefore, we propose a prompt-based length control method to achieve high-accuracy length controlled generation. In particular, we adopt reinforcement learning with the reward signal given by either trainable or rule-based reward models, which further enhances the length-control ability of LLMs by rewarding outputs that follows pre-defined control instruction. To enable rule-based inference, we also introduce standard prompt extractor to collect the standard control information from users' input. Experiments show that our method significantly improves the accuracy of prompt-based length control for summarization task on popular datasets like CNNDM and NYT. Both the standard prompt extractor and the RL-tuned model have show strong generalization ability to unseen control prompt templates.

Ensuring that generated utterances are faithful to dialogue actions is crucial for Task-Oriented Dialogue Response Generation. Slot Error Rate (SER) only partially measures generation quality in that it solely assesses utterances generated from non-categorical slots whose values are expected to be reproduced exactly. Utterances generated from categorical slots, which are more variable, are not assessed by SER. We propose Schema-Guided Semantic Accuracy (SGSAcc) to evaluate utterances generated from both categorical and non-categorical slots by recognizing textual entailment. We show that SGSAcc can be applied to evaluate utterances generated from a wide range of dialogue actions in the Schema Guided Dialogue (SGD) dataset with good agreement with human judgment. We also identify a previously overlooked weakness in generating faithful utterances from categorical slots in unseen domains. We show that prefix tuning applied to T5 generation can address this problem. We further build an ensemble of prefix-tuning and fine-tuning models that achieves the lowest SER reported and high SGSAcc on the SGD dataset.

SATNet is a differentiable constraint solver with a custom backpropagation algorithm, which can be used as a layer in a deep-learning system. It is a promising proposal for bridging deep learning and logical reasoning. In fact, SATNet has been successfully applied to learn, among others, the rules of a complex logical puzzle, such as Sudoku, just from input and output pairs where inputs are given as images. In this paper, we show how to improve the learning of SATNet by exploiting symmetries in the target rules of a given but unknown logical puzzle or more generally a logical formula. We present SymSATNet, a variant of SATNet that translates the given symmetries of the target rules to a condition on the parameters of SATNet and requires that the parameters should have a particular parametric form that guarantees the condition. The requirement dramatically reduces the number of parameters to learn for the rules with enough symmetries, and makes the parameter learning of SymSATNet much easier than that of SATNet. We also describe a technique for automatically discovering symmetries of the target rules from examples. Our experiments with Sudoku and Rubik's cube show the substantial improvement of SymSATNet over the baseline SATNet.

In this paper we present a technique for procedurally generating 3D maps using a set of premade meshes which snap together based on designer-specified visual constraints. The proposed approach avoids size and layout limitations, offering the designer control over the look and feel of the generated maps, as well as immediate feedback on a given map's navigability. A prototype implementation of the method, developed in the Unity game engine, is discussed, and a number of case studies are analyzed. These include a multiplayer game where the method was used, together with a number of illustrative examples which highlight various parameterizations and generation methods. We argue that the technique is designer-friendly and can be used as a map composition method and/or as a prototyping system in 3D level design, opening the door for quality map and level creation in a fraction of the time of a fully human-based approach.

The TriRhenaTech alliance presents a collection of accepted papers of the cancelled tri-national 'Upper-Rhine Artificial Inteeligence Symposium' planned for 13th May 2020 in Karlsruhe. The TriRhenaTech alliance is a network of universities in the Upper-Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe, and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture and management) and the University of Applied Sciences and Arts Northwestern Switzerland. The alliance's common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.

Datasets in high-dimension do not typically form clusters in their original space; the issue is worse when the number of points in the dataset is small. We propose a low-computation method to find statistically significant clustering structures in a small dataset. The method proceeds by projecting the data on a random line and seeking binary clusterings in the resulting one-dimensional data. Non-linear separations are obtained by extending the feature space using monomials of higher degrees in the original features. The statistical validity of the clustering structures obtained is tested in the projected one-dimensional space, thus bypassing the challenge of statistical validation in high-dimension. Projecting on a random line is an extreme dimension reduction technique that has previously been used successfully as part of a hierarchical clustering method for high-dimensional data. Our experiments show that with this simplified framework, statistically significant clustering structures can be found with as few as 100-200 points, depending on the dataset. The different structures uncovered are found to persist as more points are added to the dataset.

If a project uses Lightning, you can see the core of what's happening by looking in the training step… of any project! That's an incredible step towards helping achieve more reproducible deep learning code.

When evaluating machine learning models, the validation step helps you find the best parameters for your model while also preventing it from becoming overfitted. Two of the most popular strategies to perform the validation step are the hold-out strategy and the k-fold strategy. Pros of the hold-out strategy: Fully independent data; only needs to be run once so has lower computational costs. Cons of the hold-out strategy: Performance evaluation is subject to higher variance given the smaller size of the data. K-fold validation evaluates the data across the entire training set, but it does so by dividing the training set into K folds – or subsections – (where K is a positive integer) and then training the model K times, each time leaving a different fold out of the training data and using it instead as a validation set.