We introduce ComplexTempQA,a large-scale dataset consisting of over 100 million question-answer pairs designed to tackle the challenges in temporal question answering. ComplexTempQA significantly surpasses existing benchmarks like HOTPOTQA, TORQUE, and TEQUILA in scale and scope. Utilizing data from Wikipedia and Wikidata, the dataset covers questions spanning over two decades and offers an unmatched breadth of topics. We introduce a unique taxonomy that categorizes questions as attributes, comparisons, and counting questions, each revolving around events, entities, and time periods. One standout feature of ComplexTempQA is the high complexity of its questions, which demand effective capabilities for answering such as across-time comparison, temporal aggregation, and multi-hop reasoning involving temporal event ordering and entity recognition. Additionally, each question is accompanied by detailed metadata, including specific time scopes, allowing for comprehensive evaluation and enhancement of the temporal reasoning abilities of large language models. ComplexTempQA serves both as a testing ground for developing sophisticated AI models and as a foundation for advancing research in question answering, information retrieval, and language understanding. Dataset and code are freely available at: https://github.com/DataScienceUIBK/ComplexTempQA.

As AI systems are increasingly incorporated into domains where human behavior has set the norm, a challenge for AI governance and AI alignment research is to regulate their behavior in a way that is useful and constructive for society. One way to answer this question is to ask: how do we govern the human behavior that the models are emulating? To evaluate human behavior, the American legal system often uses the "Reasonable Person Standard." The idea of "reasonable" behavior comes up in nearly every area of law. The legal system often judges the actions of parties with respect to what a reasonable person would have done under similar circumstances. This paper argues that the reasonable person standard provides useful guidelines for the type of behavior we should develop, probe, and stress-test in models. It explains how reasonableness is defined and used in key areas of the law using illustrative cases, how the reasonable person standard could apply to AI behavior in each of these areas and contexts, and how our societal understanding of "reasonable" behavior provides useful technical goals for AI researchers.

Recent improvements in large language models (LLMs) have significantly enhanced natural language processing (NLP) applications. However, these models can also inherit and perpetuate biases from their training data. Addressing this issue is crucial, yet many existing datasets do not offer evaluation across diverse NLP tasks. To tackle this, we introduce the Bias Evaluations Across Domains (BEADs) dataset, designed to support a wide range of NLP tasks, including text classification, bias entity recognition, bias quantification, and benign language generation. BEADs uses AI-driven annotation combined with experts' verification to provide reliable labels. This method overcomes the limitations of existing datasets that typically depend on crowd-sourcing, expert-only annotations with limited bias evaluations, or unverified AI labeling. Our empirical analysis shows that BEADs is effective in detecting and reducing biases across different language models, with smaller models fine-tuned on BEADs often outperforming LLMs in bias classification tasks. However, these models may still exhibit biases towards certain demographics. Fine-tuning LLMs with our benign language data also reduces biases while preserving the models' knowledge. Our findings highlight the importance of comprehensive bias evaluation and the potential of targeted fine-tuning for reducing the bias of LLMs. We are making BEADs publicly available at https://huggingface.co/datasets/shainar/BEAD Warning: This paper contains examples that may be considered offensive.

This is a long paper, an essay, on ambiguity, pragmatics, legal ecosystems, and the expressive function of law. It is divided into two parts and fifteen sections. The first part (Pragmatics) addresses ambiguity from the perspective of linguistic and cognitive pragmatics in the legal field. The second part (Computing) deals with this issue from the point of view of human-centered design and artificial intelligence, specifically focusing on the notion and modelling of rules and what it means to comply with the rules. This is necessary for the scaffolding of smart legal ecosystems (SLE). I will develop this subject with the example of the architecture, information flows, and smart ecosystem of OPTIMAI, an EU project of Industry 4.0 for zero-defect manufacturing (Optimizing Manufacturing Processes through Artificial Intelligence and Virtualization).

Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora used for safety alignment of LLMs are solely interpreted by semantics. This assumption, however, does not hold in real-world applications, which leads to severe vulnerabilities in LLMs. For example, users of forums often use ASCII art, a form of text-based art, to convey image information. In this paper, we propose a novel ASCII art-based jailbreak attack and introduce a comprehensive benchmark Vision-in-Text Challenge (ViTC) to evaluate the capabilities of LLMs in recognizing prompts that cannot be solely interpreted by semantics. We show that five SOTA LLMs (GPT-3.5, GPT-4, Gemini, Claude, and Llama2) struggle to recognize prompts provided in the form of ASCII art. Based on this observation, we develop the jailbreak attack ArtPrompt, which leverages the poor performance of LLMs in recognizing ASCII art to bypass safety measures and elicit undesired behaviors from LLMs. ArtPrompt only requires black-box access to the victim LLMs, making it a practical attack. We evaluate ArtPrompt on five SOTA LLMs, and show that ArtPrompt can effectively and efficiently induce undesired behaviors from all five LLMs. Our code is available at https://github.com/uw-nsl/ArtPrompt.

Integrating machine learning into Automated Control Systems (ACS) enhances decision-making in industrial process management. One of the limitations to the widespread adoption of these technologies in industry is the vulnerability of neural networks to adversarial attacks. This study explores the threats in deploying deep learning models for fault diagnosis in ACS using the Tennessee Eastman Process dataset. By evaluating three neural networks with different architectures, we subject them to six types of adversarial attacks and explore five different defense methods. Our results highlight the strong vulnerability of models to adversarial samples and the varying effectiveness of defense strategies. We also propose a novel protection approach by combining multiple defense methods and demonstrate it's efficacy. This research contributes several insights into securing machine learning within ACS, ensuring robust fault diagnosis in industrial processes.

Temporal Knowledge Graph (TKG) forecasting aims to predict future facts based on given histories. Most recent graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities. Nowadays, with the surge of LLMs, the LLM-based TKG prediction model has emerged. However, the existing LLM-based model exhibits three shortcomings: (1) It only focuses on the first-order history for prediction while ignoring high-order historical information, resulting in the provided information for LLMs being extremely limited. (2) LLMs struggle with optimal reasoning performance under heavy historical information loads. (3) For TKG prediction, the temporal reasoning capability of LLM alone is limited. To address the first two challenges, we propose Chain-of-History (CoH) reasoning which explores high-order histories step-by-step, achieving effective utilization of high-order historical information for LLMs on TKG prediction. To address the third issue, we design CoH as a plug-and-play module to enhance the performance of graph-based models for TKG prediction. Extensive experiments on three datasets and backbones demonstrate the effectiveness of CoH.

Reinforcement Learning from Human Feedback (RLHF) (Christiano et al., 2017) has rapidly become a standard method to align Large Language Models (LLMs). One of the main practical issues that all the prominent existing RLHF methods (offline or online) (Ouyang et al., 2022; Rafailov et al., 2023; Azar et al., 2023; Zhao et al., 2023b; Ahmadian et al., 2024) encounter is that their optimal solution heavily depends on the training task in terms of the distribution used to generate the preference data (behavior policy) (Munos et al., 2023; Azar et al., 2023). This makes the existing RLHF methods prone to out-of-distribution (OOD) tasks (Li et al., 2024; Kirk et al., 2024) where the evaluation distribution is significantly different from that of the behavior policy. Also, whenever the base/SFT models significantly differ from the behavior policy, the dependency of the RLHF solutions on the behavior policy makes the preference dataset and reward model less useful (Gao et al., 2022) as RLHF may undo the SFT/pretraining. To address this challenge, we introduce an alternative approach for aligning LLMs from human preferences based on more principled and robust foundations. Our goal is to find a solution that is robust to the changes in the preference dataset, meaning that changes in the distribution from which the completions are sampled do not affect the final outcome of learning significantly. To achieve this goal, we exploit the concept of self-improving (Huang et al., 2022; Bai et al., 2022) language models. By self-improving LLM we refer to a model capable of enhancing its outputs recursively with each inference iteration.

Last year the White House struck a landmark safety deal with AI developers that saw companies including Google and OpenAI promise to consider what could go wrong when they created software like that behind ChatGPT. Now a former domestic policy adviser to President Biden who helped forge that deal says that AI developers need to step up on another front: protecting their secret formulas from China. "Because they are behind, they are going to want to take advantage of what we have," said Rice of China. She left the White House last year and spoke on Wednesday during a panel about AI and geopolitics at an event hosted by Stanford University's Human-Centered AI research institute. We really do need to look at this whole spectrum of how do we stay ahead, and I worry that on the security side, we are lagging."

The compound that was hit had been operated by UNRWA, the main U.N. body that aids Palestinians in Gaza. Philippe Lazzarini, the director of UNRWA, wrote on social media that 6,000 Palestinians had been sheltering in the school complex. Khalil Daqran, a spokesman for Al Aqsa Martyrs Hospital in the central Gaza city of Deir al Balah, said the bodies of at least 40 people killed in the attack had been brought to the hospital. At least some of the victims were women, children and older people, he added, although he declined to provide a precise figure. Colonel Lerner, the Israeli military spokesman, said he was "not aware of any civilian casualties" as a result of the strike. U.S. officials have been encouraging the Israeli military for months to use GBU-39s, which weigh at least 250 pounds, rather than larger 2,000-pound bombs because they are generally more precise.