Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation. However, their effectiveness in supporting domain-specific writing, particularly in business contexts, is relatively less explored. Our formative study with industry professionals revealed the limitations in current LLMs' understanding of the nuances in such domain-specific writing. To address this gap, we propose an approach of human-AI collaborative taxonomy development to perform as a guideline for domain-specific writing assistants. This method integrates iterative feedback from domain experts and multiple interactions between these experts and LLMs to refine the taxonomy. Through larger-scale experiments, we aim to validate this methodology and thus improve LLM-powered writing assistance, tailoring it to meet the unique requirements of different stakeholder needs.

With rapid advances in machine learning, many people in the field have been discussing the rise of digital minds and the possibility of artificial sentience. Future developments in AI capabilities and safety will depend on public opinion and human-AI interaction. To begin to fill this research gap, we present the first nationally representative survey data on the topic of sentient AI: initial results from the Artificial Intelligence, Morality, and Sentience (AIMS) survey, a preregistered and longitudinal study of U.S. public opinion that began in 2021. Across one wave of data collection in 2021 and two in 2023 (total N = 3,500), we found mind perception and moral concern for AI well-being in 2021 were higher than predicted and significantly increased in 2023: for example, 71% agree sentient AI deserve to be treated with respect, and 38% support legal rights. People have become more threatened by AI, and there is widespread opposition to new technologies: 63% support a ban on smarter-than-human AI, and 69% support a ban on sentient AI. Expected timelines are surprisingly short and shortening with a median forecast of sentient AI in only five years and artificial general intelligence in only two years. We argue that, whether or not AIs become sentient, the discussion itself may overhaul human-computer interaction and shape the future trajectory of AI technologies, including existential risks and opportunities.

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size. Specifically, for each model, we find a single direction such that erasing this direction from the model's residual stream activations prevents it from refusing harmful instructions, while adding this direction elicits refusal on even harmless instructions. Leveraging this insight, we propose a novel white-box jailbreak method that surgically disables refusal with minimal effect on other capabilities. Finally, we mechanistically analyze how adversarial suffixes suppress propagation of the refusal-mediating direction. Our findings underscore the brittleness of current safety fine-tuning methods. More broadly, our work showcases how an understanding of model internals can be leveraged to develop practical methods for controlling model behavior.

Personal names simultaneously differentiate individuals and categorize them in ways that are important in a given society. While the natural language processing community has thus associated personal names with sociodemographic characteristics in a variety of tasks, researchers have engaged to varying degrees with the established methodological problems in doing so. To guide future work that uses names and sociodemographic characteristics, we provide an overview of relevant research: first, we present an interdisciplinary background on names and naming. We then survey the issues inherent to associating names with sociodemographic attributes, covering problems of validity (e.g., systematic error, construct validity), as well as ethical concerns (e.g., harms, differential impact, cultural insensitivity). Finally, we provide guiding questions along with normative recommendations to avoid validity and ethical pitfalls when dealing with names and sociodemographic characteristics in natural language processing.

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness in solving questions. Context compression tackles this issue by filtering out irrelevant information, but current methods still struggle in realistic scenarios where crucial information cannot be captured with a single-step approach. To overcome this limitation, we introduce CompAct, a novel framework that employs an active strategy to condense extensive documents without losing key information. Our experiments demonstrate that CompAct brings significant improvements in both performance and compression rate on multi-hop question-answering (QA) benchmarks. CompAct flexibly operates as a cost-efficient plug-in module with various off-the-shelf retrievers or readers, achieving exceptionally high compression rates (47x).

OpenAI whistleblowers have urged the US financial watchdog to investigate non-disclosure agreements at the startup after claiming the contracts included restrictions such as requiring employees to seek permission before contacting regulators. Non-disclosure agreements (NDAs) typically bar an employee from sharing company information with outside parties but a group of whistleblowers are arguing that OpenAI's agreements could have led to workers being punished for raising concerns about the company to federal authorities. San Francisco-based OpenAI is the developer of the ChatGPT chatbot and a key player in the artificial intelligence boom, which has been accompanied by expressions of concern from experts about the potential dangerous capabilities of the technology. "Given the well-documented potential risks posed by the irresponsible deployment of AI, we urge the Commissioners to immediately approve an investigation into OpenAI's prior NDAs, and to review current efforts apparently being undertaken by the company to ensure full compliance with SEC rules," the letter to Gary Gensler, the chair of the US Securities and Exchange Commission (SEC), said. The letter from whistleblower representatives was sent on 1 July and published by the Washington Post on Saturday after the news organisation obtained it from the office of the US senator Chuck Grassley.

An entity defending itself against infringement may attempt to A key capability in managing patent applications or a patent invalidate a patent by finding novelty-destroying prior art to that portfolio is comparing claims to other text, e.g. a patent patent. In all cases, the key task is to search through a set of specification. Because the language of claims is different from documents and determine whether those documents cover all language used elsewhere in the patent application or in non-patent aspects of each claim of the subject patent application or granted text, this has been challenging for computer based natural patent. Thus, a claim of a subject patent (application) may be language processing. We test two new LLM-based approaches considered a query to an information retrieval system whose and find that both provide substantially better performance than objective is to retrieve a document or set of documents that previously published values. The ability to match dense contain all aspects of that claim.

Predicting emotions elicited by news headlines can be challenging as the task is largely influenced by the varying nature of people's interpretations and backgrounds. Previous works have explored classifying discrete emotions directly from news headlines. We provide a different approach to tackling this problem by utilizing people's explanations of their emotion, written in free-text, on how they feel after reading a news headline. Using the dataset BU-NEmo+ (Gao et al., 2022), we found that for emotion classification, the free-text explanations have a strong correlation with the dominant emotion elicited by the headlines. The free-text explanations also contain more sentimental context than the news headlines alone and can serve as a better input to emotion classification models. Therefore, in this work we explored generating emotion explanations from headlines by training a sequence-to-sequence transformer model and by using pretrained large language model, ChatGPT (GPT-4). We then used the generated emotion explanations for emotion classification. In addition, we also experimented with training the pretrained T5 model for the intermediate task of explanation generation before fine-tuning it for emotion classification. Using McNemar's significance test, methods that incorporate GPT-generated free-text emotion explanations demonstrated significant improvement (P-value < 0.05) in emotion classification from headlines, compared to methods that only use headlines. This underscores the value of using intermediate free-text explanations for emotion prediction tasks with headlines.

Evaluating the bias in Large Language Models (LLMs) becomes increasingly crucial with their rapid development. However, existing evaluation methods rely on fixed-form outputs and cannot adapt to the flexible open-text generation scenarios of LLMs (e.g., sentence completion and question answering). To address this, we introduce BiasAlert, a plug-and-play tool designed to detect social bias in open-text generations of LLMs. BiasAlert integrates external human knowledge with inherent reasoning capabilities to detect bias reliably. Extensive experiments demonstrate that BiasAlert significantly outperforms existing state-of-the-art methods like GPT4-as-A-Judge in detecting bias. Furthermore, through application studies, we demonstrate the utility of BiasAlert in reliable LLM bias evaluation and bias mitigation across various scenarios. Model and code will be publicly released.

Dark patterns, design tricks used on online interfaces to manipulate users decision-making process, have raised public concerns. However, research on regulation of dark pattern remains underdeveloped and scattered, particularly regarding scholars views on the concept, regulatory paradigms, and solutions. Following PRISMA guidelines, this paper systematically reviews the formats and content of regulatory discussions on dark patterns from the interdisciplinary scholarship of Law and Human-Computer Interaction. A total of 65 studies were analysed through content and thematic analysis. This study synthesises the unique trends and characteristics of legal scholarship on dark patterns, identifying five root problems and triple layered harms. It critiques current regulations in terms of legal theories and sectoral legislations, highlighting their inadequacies in addressing dark patterns. The paper also critically examines existing proposed solutions, including paradigmatic shifts in legal doctrines, refinements to existing frameworks, technical design-embedded solutions, and accountability measures for design practices. This research critically discusses the current barriers to effective dark pattern regulations and explores promising regulatory solutions. The difficulty in identifying the normative nature of various forms of dark patterns, in identifying evident and actionable harm, and the expanding scope of dark patterns connotation inherently hinders effective regulation. However, technical design-embedded solutions, accountability frameworks, and practical design guidelines offer potential routes for more proactive regulation, while legal pluralism stands as a promising macro-level change in regulatory paradigms for dark pattern regulation.