Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e.g., computer agents are not capable of characterful utterance or situational lying). We propose a werewolf agent that solves some of those difficulties by combining a Large Language Model (LLM) and a rule-based algorithm. In particular, our agent uses a rule-based algorithm to select an output either from an LLM or a template prepared beforehand based on the results of analyzing conversation history using an LLM. It allows the agent to refute in specific situations, identify when to end the conversation, and behave with persona. This approach mitigated conversational inconsistencies and facilitated logical utterance as a result. We also conducted a qualitative evaluation, which resulted in our agent being perceived as more human-like compared to an unmodified LLM. The agent is freely available for contributing to advance the research in the field of Werewolf game.

Reinforcement learning (RL) provides a compelling framework for enabling autonomous vehicles to continue to learn and improve diverse driving behaviors on their own. However, training real-world autonomous vehicles with current RL algorithms presents several challenges. One critical challenge, often overlooked in these algorithms, is the need to reset a driving environment between every episode. While resetting an environment after each episode is trivial in simulated settings, it demands significant human intervention in the real world. In this paper, we introduce a novel autonomous algorithm that allows off-the-shelf RL algorithms to train an autonomous vehicle with minimal human intervention. Our algorithm takes into account the learning progress of the autonomous vehicle to determine when to abort episodes before it enters unsafe states and where to reset it for subsequent episodes in order to gather informative transitions. The learning progress is estimated based on the novelty of both current and future states. We also take advantage of rule-based autonomous driving algorithms to safely reset an autonomous vehicle to an initial state. We evaluate our algorithm against baselines on diverse urban driving tasks. The experimental results show that our algorithm is task-agnostic and achieves better driving performance with fewer manual resets than baselines.

This paper presents our submission to the SemEval 2024 Task 5: The Legal Argument Reasoning Task in Civil Procedure. We present two approaches to solving the task of legal answer validation, given an introduction to the case, a question and an answer candidate. Firstly, we fine-tuned pre-trained BERT-based models and found that models trained on domain knowledge perform better. Secondly, we performed few-shot prompting on GPT models and found that reformulating the answer validation task to be a multiple-choice QA task remarkably improves the performance of the model. Our best submission is a BERT-based model that achieved the 7th place out of 20.

A recent debate on so called Foundation models (CRFM) brings a real question of if we can build very large models on any specified domain, similar to current large language models, and replace our ...

This paper presents the D2KLab team's approach to the RecSys Challenge 2019 which focuses on the task of recommending accommodations based on user sessions. What is the feeling of a person who says "Rooms of the hotel are enormous, staff are friendly and efficient"? It is positive. Similarly to the sequence of words in a sentence where one can affirm what the feeling is, analysing a sequence of actions performed by a user in a website can lead to predict what will be the item the user will add to his basket at the end of the shopping session. We propose to use a many-to-one recurrent neural network that learns the probability that a user will click on an accommodation based on the sequence of actions he has performed during his browsing session. More specifically, we combine a rule-based algorithm with a Gated Recurrent Unit RNN in order to sort the list of accommodations that is shown to the user. We optimized the RNN on a validation set, tuning the hyper-parameters such as the learning rate, the batch-size and the accommodation embedding size. This analogy with the sentiment analysis task gives promising results. However, it is computationally demanding in the training phase and it needs to be further tuned.

Algorithmic decision making has proliferated and now impacts our daily lives in both mundane and consequential ways. Machine learning practitioners make use of a myriad of algorithms for predictive models in applications as diverse as movie recommendations, medical diagnoses, and parole recommendations without delving into the reasons driving specific predictive decisions. Machine learning algorithms in such applications are often chosen for their superior performance, however popular choices such as random forest and deep neural networks fail to provide an interpretable understanding of the predictive model. In recent years, rule-based algorithms have been used to address this issue. Wang et al. (2017) presented an or-of-and (disjunctive normal form) based classification technique that allows for classification rule mining of a single class in a binary classification; this method is also shown to perform comparably to other modern algorithms. In this work, we extend this idea to provide classification rules for both classes simultaneously. That is, we provide a distinct set of rules for both positive and negative classes. In describing this approach, we also present a novel and complete taxonomy of classifications that clearly capture and quantify the inherent ambiguity in noisy binary classifications in the real world. We show that this approach leads to a more granular formulation of the likelihood model and a simulated-annealing based optimization achieves classification performance competitive with comparable techniques. We apply our method to synthetic as well as real world data sets to compare with other related methods that demonstrate the utility of our proposal.

Interpretability is becoming increasingly important in predictive model analysis. Unfortunately, as mentioned by many authors, there is still no consensus on that idea. The aim of this article is to propose a rigorous mathematical definition of the concept of interpretability, allowing fair comparisons between any rule-based algorithms. This definition is built from three notions, each of which being quantitatively measured by a simple formula: predictivity, stability and simplicity. While predictivity has been widely studied to measure the accuracy of predictive algorithms, stability is based on the Dice-Sorensen index to compare two sets of rules generated by an algorithm using two independent samples. Simplicity is based on the sum of the length of the rules deriving from the generated model. The final objective measure of the interpretability of any rule-based algorithm ends up as a weighted sum of the three aforementioned concepts. This paper concludes with the comparison of the interpretability between four rule-based algorithms.

Finding hard instances, which need a long time to solve, of graph problems such as the graph coloring problem and the maximum clique problem, is important for (1) building a good benchmark for evaluating the performance of algorithms, and (2) analyzing the algorithms to accelerate them. The existing methods for generating hard instances rely on parameters or rules that are found by domain experts; however, they are specific to the problem. Hence, it is difficult to generate hard instances for general cases. To address this issue, in this paper, we formulate finding hard instances of graph problems as two equivalent optimization problems. Then, we propose a method to automatically find hard instances by solving the optimization problems. The advantage of the proposed algorithm over the existing rule based approach is that it does not require any task specific knowledge. To the best of our knowledge, this is the first non-trivial method in the literature to automatically find hard instances. Through experiments on various problems, we demonstrate that our proposed method can generate instances that are a few to several orders of magnitude harder than the random based approach in many settings. In particular, our method outperforms rule-based algorithms in the 3-coloring problem.

Here at DivvyHQ, we love a good showdown. Take for example, the a-cappella Riff-off from Pitch Perfect 2. So good, right? As technology advances, many journalists, writers, brands and content marketers have reacted by pitting technology against humans with the same Hollywood flare used in all the films mentioned above. Are robo-bosses set to replace management? Will AI software soon write blog posts better than humans?! God help us no! Are Japanese robots replacing creative directors?

Taking a hybrid approach of using both a rule-based algorithm created by expert humans and statistical algorithms where appropriate, gives a number of key advantages over purely statistical systems. Building such hybrid systems requires less data and might well take less time. The choice of development tools can also make a big difference to the final result. Some natural language development platforms include not only the development tools themselves, but also curated data resources and the tools for expanding them. With a rule-based algorithm, coupled with machine learning algorithms, curated data and a development platform with a sophisticated graphical user interface, humans can easily construct the intelligence behind human-machine conversations to ensure that natural language applications properly understand the context of the conversation – every time.