Recent advances in large language models (LLMs) have intensified the need to understand and reliably curb their harmful behaviours. We introduce a multidimensional framework for probing and steering harmful content in model internals. For each of 55 distinct harmfulness subconcepts (e.g., racial hate, employment scams, weapons), we learn a linear probe, yielding 55 interpretable directions in activation space. Collectively, these directions span a harmfulness subspace that we show is strikingly low-rank. We then test ablation of the entire subspace from model internals, as well as steering and ablation in the subspace's dominant direction. We find that dominant direction steering allows for near elimination of harmfulness with a low decrease in utility. Our findings advance the emerging view that concept subspaces provide a scalable lens on LLM behaviour and offer practical tools for the community to audit and harden future generations of language models.

As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical. While prior work has largely focused on improving LLM performance in these domains, it has often neglected the evaluation of domain-specific safety risks. To bridge this gap, we first define domain-specific safety principles for LLMs based on the AMA Principles of Medical Ethics, the ABA Model Rules of Professional Conduct, and the CFA Institute Code of Ethics. Building on this foundation, we introduce Trident-Bench, a benchmark specifically targeting LLM safety in the legal, financial, and medical domains. We evaluated 19 general-purpose and domain-specialized models on Trident-Bench and show that it effectively reveals key safety gaps -- strong generalist models (e.g., GPT, Gemini) can meet basic expectations, whereas domain-specialized models often struggle with subtle ethical nuances. This highlights an urgent need for finer-grained domain-specific safety improvements. By introducing Trident-Bench, our work provides one of the first systematic resources for studying LLM safety in law and finance, and lays the groundwork for future research aimed at reducing the safety risks of deploying LLMs in professionally regulated fields. Code and benchmark will be released at: https://github.com/zackhuiiiii/TRIDENT

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390 experimental responses from three major LLMs (Claude, GPT-4, Gemini) across 10 task domains under 6 threat conditions. We introduce a novel threat taxonomy and multi-metric evaluation framework to quantify both negative manipulation effects and positive performance improvements. Results reveal systematic vulnerabilities, with policy evaluation showing the highest metric significance rates under role-based threats, alongside substantial performance enhancements in numerous cases with effect sizes up to +1336%. Statistical analysis indicates systematic certainty manipulation (pFDR < 0.0001) and significant improvements in analytical depth and response quality. These findings have dual implications for AI safety and practical prompt engineering in high-stakes applications.

This paper presents a comprehensive refutation of the so-called "blockchain trilemma," a widely cited but formally ungrounded claim asserting an inherent trade-off between decentralisation, security, and scalability in blockchain protocols. Through formal analysis, empirical evidence, and detailed critique of both methodology and terminology, we demonstrate that the trilemma rests on semantic equivocation, misuse of distributed systems theory, and a failure to define operational metrics. Particular focus is placed on the conflation of topological network analogies with protocol-level architecture, the mischaracterisation of Bitcoin's design--including the role of miners, SPV clients, and header-based verification--and the failure to ground claims in complexity-theoretic or adversarial models. By reconstructing Bitcoin as a deterministic, stateless distribution protocol governed by evidentiary trust, we show that scalability is not a trade-off but an engineering outcome. The paper concludes by identifying systemic issues in academic discourse and peer review that have allowed such fallacies to persist, and offers formal criteria for evaluating future claims in blockchain research.

Given the large size and volumes of contracts and their underlying inherent complexity, manual reviews become inefficient and prone to errors, creating a clear need for automation. Automatic Legal Contract Classification (LCC) revolutionizes the way legal contracts are analyzed, offering substantial improvements in speed, accuracy, and accessibility. This survey delves into the challenges of automatic LCC and a detailed examination of key tasks, datasets, and methodologies. We identify seven classification tasks within LCC, and review fourteen datasets related to English-language contracts, including public, proprietary, and non-public sources. We also introduce a methodology taxonomy for LCC, categorized into Traditional Machine Learning, Deep Learning, and Transformer-based approaches. Additionally, the survey discusses evaluation techniques and highlights the best-performing results from the reviewed studies. By providing a thorough overview of current methods and their limitations, this survey suggests future research directions to improve the efficiency, accuracy, and scalability of LCC. As the first comprehensive survey on LCC, it aims to support legal NLP researchers and practitioners in improving legal processes, making legal information more accessible, and promoting a more informed and equitable society.

Conversational agents (CA s) based on generative artificial intelligence frequently face challenges ensuring ethical interactions that align with human values. Current value alignment efforts largely rely on top - down approaches, such as technical guidelines or legal value principles. However, these methods tend to be disconnec ted from the specific contexts in which CAs operate, potentially leading to misalignment with users' interests. To address this challenge, we propose a novel, bottom - up approach to value alignment, utilizing the value ontology of the ISO Value - Based Engine ering standard for ethical IT design. We analyse 593 ethically sensitive system outputs identified from 16,908 conversational logs of a major European employment service CA to identify core values and instances of value misalignment within real - world inter actions. The results revealed nine core values and 32 different value misalignments that negatively impacted users. Our findings provide actionable insights for CA providers seeking to address ethical challenges and achieve more context - sensitive value ali gnment.

As AI systems shape individual and societal decisions, fostering critical AI literacy is essential. Traditional approaches--such as blog articles, static lessons, and social media discussions--often fail to support deep conceptual understanding and critical engagement. This study examines whether interactive simulations can help learners "think like a scientist" by engaging them in hypothesis testing, experimentation, and direct observation of AI behavior. In a controlled study with 605 participants, we assess how interactive AI tutorials impact learning of key concepts such as fairness, dataset representativeness, and bias in language models. Results show that interactive simulations effectively enhance AI literacy across topics, supporting greater knowledge transfer and self-reported confidence, though engagement alone does not predict learning. This work contributes to the growing field of AI literacy education, highlighting how interactive, inquiry-driven methodologies can better equip individuals to critically engage with AI in their daily lives.

Social media platforms increasingly employ proactive moderation techniques, such as detecting and curbing toxic and uncivil comments, to prevent the spread of harmful content. Despite these efforts, such approaches are often criticized for creating a climate of censorship and failing to address the underlying causes of uncivil behavior. Our work makes both theoretical and practical contributions by proposing and evaluating two types of emotion monitoring dashboards to users' emotional awareness and mitigate hate speech. In a study involving 211 participants, we evaluate the effects of the two mechanisms on user commenting behavior and emotional experiences. The results reveal that these interventions effectively increase users' awareness of their emotional states and reduce hate speech. However, our findings also indicate potential unintended effects, including increased expression of negative emotions (Angry, Fear, and Sad) when discussing sensitive issues. These insights provide a basis for further research on integrating proactive emotion regulation tools into social media platforms to foster healthier digital interactions.

Current AI systems rely on opaque reasoning processes that hinder human oversight and collaborative potential. Conventional explainable AI approaches offer post-hoc justifications and often fail to establish genuine symbiotic collaboration. In this paper, the Symbiotic Epistemology is presented as a philosophical foundation for human-AI cognitive partnerships. Unlike frameworks that treat AI as a mere tool or replacement, symbiotic epistemology positions AI as a reasoning partner, fostering calibrated trust by aligning human confidence with AI reliability through explicit reasoning patterns and confidence assessments. SynLang (Symbiotic Syntactic Language) is introduced as a formal protocol for transparent human-AI collaboration. The framework is empirically validated through actual human-AI dialogues demonstrating AI's adaptation to structured reasoning protocols and successful metacognitive intervention. The protocol defines two complementary mechanisms: TRACE for high-level reasoning patterns and TRACE_FE for detailed factor explanations. It also integrates confidence quantification, declarative control over AI behavior, and context inheritance for multi-agent coordination. By structuring communication and embedding confidence-calibrated transparency, SynLang, together with symbiotic epistemology, enables AI systems that enhance human intelligence, preserve human agency, and uphold ethical accountability in collaborative decision-making. Through dual-level transparency, beginning with high-level reasoning patterns and progressing to granular explanations, the protocol facilitates rapid comprehension and supports thorough verification of AI decision-making.

Large language models (LLMs) like GPT-3 and BERT have revolutionized natural language processing (NLP), yet their environmental costs remain dangerously overlooked. This article critiques the sustainability of LLMs, quantifying their carbon footprint, water usage, and contribution to e-waste through case studies of models such as GPT-4 and energy-efficient alternatives like Mistral 7B. Training a single LLM can emit carbon dioxide equivalent to hundreds of cars driven annually, while data centre cooling exacerbates water scarcity in vulnerable regions. Systemic challenges corporate greenwashing, redundant model development, and regulatory voids perpetuate harm, disproportionately burdening marginalized communities in the Global South. However, pathways exist for sustainable NLP: technical innovations (e.g., model pruning, quantum computing), policy reforms (carbon taxes, mandatory emissions reporting), and cultural shifts prioritizing necessity over novelty. By analysing industry leaders (Google, Microsoft) and laggards (Amazon), this work underscores the urgency of ethical accountability and global cooperation. Without immediate action, AIs ecological toll risks outpacing its societal benefits. The article concludes with a call to align technological progress with planetary boundaries, advocating for equitable, transparent, and regenerative AI systems that prioritize both human and environmental well-being.