Mediation is often treated as an extension of negotiation, without taking into account the unique role that norms and facts play in legal mediation. Additionally, current approaches for updating argument acceptability in response to changing variables frequently require the introduction of new arguments or the removal of existing ones, which can be inefficient and cumbersome in decision-making processes within legal disputes. In this paper, our contribution is two-fold. First, we introduce a QuAM (Quantitative Argumentation Mediate) framework, which integrates the parties' knowledge and the mediator's knowledge, including facts and legal norms, when determining the acceptability of a mediation goal. Second, we develop a new formalism to model the relationship between the acceptability of a goal argument and the values assigned to a variable associated with the argument. We use a real-world legal mediation as a running example to illustrate our approach.

Automated red teaming is an effective method for identifying misaligned behaviors in large language models (LLMs). Existing approaches, however, often focus primarily on improving attack success rates while overlooking the need for comprehensive test case coverage. Additionally, most of these methods are limited to single-turn red teaming, failing to capture the multi-turn dynamics of real-world human-machine interactions. To overcome these limitations, we propose HARM (Holistic Automated Red teaMing), which scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy. Our method also leverages a novel fine-tuning strategy and reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner. Experimental results demonstrate that our framework enables a more systematic understanding of model vulnerabilities and offers more targeted guidance for the alignment process.

This paper proposes a novel prompt engineering technique called Judgment of Thought (JoT) that is specifically tailored for binary logical reasoning tasks. JoT employs three roles$\unicode{x2014}$lawyer, prosecutor, and judge$\unicode{x2014}$to facilitate more reliable and accurate reasoning by the model. In this framework, the judge utilizes a high$\unicode{x2010}$level model, while the lawyer and prosecutor utilize low$\unicode{x2010}$level models. This structure helps the judge better understand the responses from both the lawyer and prosecutor, enabling a more accurate judgment. Experimental results on large language model (LLM) benchmark datasets, such as BigBenchHard and Winogrande, demonstrate that JoT outperforms existing methods, including Chain of Thought (CoT) and Self$\unicode{x2010}$Consistency (SC), in binary logical reasoning tasks. Additionally, in real$\unicode{x2010}$world tasks, such as Fake News Detection and SMS Spam Detection, JoT shows comparable or improved performance compared to existing techniques. JoT significantly enhances the accuracy and reliability of models in binary reasoning tasks and show potential for practical applicability across various domains. Future research should aim to further broaden the applicability of JoT and optimize its implementation for real$\unicode{x2010}$world problem$\unicode{x2010}$solving.

While many online services provide privacy policies for end users to read and understand what personal data are being collected, these documents are often lengthy and complicated. As a result, the vast majority of users do not read them at all, leading to data collection under uninformed consent. Several attempts have been made to make privacy policies more user friendly by summarising them, providing automatic annotations or labels for key sections, or by offering chat interfaces to ask specific questions. With recent advances in Large Language Models (LLMs), there is an opportunity to develop more effective tools to parse privacy policies and help users make informed decisions. In this paper, we propose an entailment-driven LLM based framework to classify paragraphs of privacy policies into meaningful labels that are easily understood by users. The results demonstrate that our framework outperforms traditional LLM methods, improving the F1 score in average by 11.2%. Additionally, our framework provides inherently explainable and meaningful predictions.

He used to go to the Regal City North cinema in Chicago three times a week. But he never goes there anymore--because of the parking lot. The parking garage, which is directly connected to the theater, once charged 2 for parking. Then it fell into disrepair sometime during the pandemic. "Someone destroyed the crossbar at the exit, and the stairwells had broken glass in them. They never replaced the glass for the stairwell," Spencer told me.

Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant documents from a corpus like Wikipedia, whereas the latter uses generative models such as Large Language Models (LLMs) to generate the context. In this paper, we introduce a novel context preparation approach called HINTQA, which employs Automatic Hint Generation (HG) techniques. Unlike traditional methods, HINTQA prompts LLMs to produce hints about potential answers for the question rather than generating relevant context. We evaluate our approach across three QA datasets including TriviaQA, NaturalQuestions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that the HINTQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts.

Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current research findings and discusses the implications of biases in real-world applications. Additionally, we critically assess existing bias mitigation techniques and propose future research directions to enhance fairness and equity in LLMs. This survey serves as a foundational resource for researchers, practitioners, and policymakers concerned with addressing and understanding biases in LLMs.

As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents - harm events to individuals and society. As a result, industry, civil society, and governments worldwide are developing best practices and regulations for monitoring and analyzing AI incidents. The AI Incident Database (AIID) is a project that catalogs AI incidents and supports further research by providing a platform to classify incidents for different operational and research-oriented goals. This study reviews the AIID's dataset of 750+ AI incidents and two independent taxonomies applied to these incidents to identify common challenges to indexing and analyzing AI incidents. We find that certain patterns of AI incidents present structural ambiguities that challenge incident databasing and explore how epistemic uncertainty in AI incident reporting is unavoidable. We therefore report mitigations to make incident processes more robust to uncertainty related to cause, extent of harm, severity, or technical details of implicated systems. With these findings, we discuss how to develop future AI incident reporting practices.

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks (e.g., long-context understanding), and many benchmarks have been proposed. However, we observe that long text generation capabilities are not well investigated. Therefore, we introduce the Hierarchical Long Text Generation Benchmark (HelloBench), a comprehensive, in-the-wild, and open-ended benchmark to evaluate LLMs' performance in generating long text. Based on Bloom's Taxonomy, HelloBench categorizes long text generation tasks into five subtasks: open-ended QA, summarization, chat, text completion, and heuristic text generation. Besides, we propose Hierarchical Long Text Evaluation (HelloEval), a human-aligned evaluation method that significantly reduces the time and effort required for human evaluation while maintaining a high correlation with human evaluation. We have conducted extensive experiments across around 30 mainstream LLMs and observed that the current LLMs lack long text generation capabilities. Specifically, first, regardless of whether the instructions include explicit or implicit length constraints, we observe that most LLMs cannot generate text that is longer than 4000 words. Second, we observe that while some LLMs can generate longer text, many issues exist (e.g., severe repetition and quality degradation). Third, to demonstrate the effectiveness of HelloEval, we compare HelloEval with traditional metrics (e.g., ROUGE, BLEU, etc.) and LLM-as-a-Judge methods, which show that HelloEval has the highest correlation with human evaluation. We release our code in https://github.com/Quehry/HelloBench.

Rapid advances in Artificial Intelligence (AI) are generating much controversy in society, often without scientific basis. As occurred the development of other emerging technologies, such as the introduction of electricity in the early 20th century, AI causes both fascination and fear. Following the advice of the philosopher R.W. Emerson's advice'the knowledge is the antidote to fear', this paper seeks to contribute to the dissemination of knowledge about AI. To this end, it reflects on the following questions: the origins of AI, its possible future evolution, its ability to show feelings, the associated threats and dangers, and the concept of AI singularity Keywords: Artificial Intelligence (AI), Fourth Industrial Revolution, Beginnings of AI, Development of AI, Automatic learning, Machine learning, Feelings in AI, Dangers of AI, Advantages of AI, Singularity of AI, Superintelligence, Frictionless Reproducibility (FR), Large Language Models, General AI (GAI), Intelligence, GPT Chat.