Alignment papers

Browse recent papers, open the full write-up, or filter the archive by topic.

213 papers found

ReviewPaperPublishedTopics

6.8ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use AgentsUnderstanding and addressing AI misalignment in everyday settings is crucial for ensuring the safe deployment of autonomous agents in real-world applications.Oct 3, 2026Agent Safety Alignment

7.5Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussionUnderstanding verbal tics in LLMs is crucial for improving human-AI interactions and addressing the alignment challenges in current training paradigms.Oct 2, 2026LLM Evaluation Alignment

6.8Emergent alignment and the projectability of ethical personasUnderstanding how language models can be aligned with ethical frameworks is crucial for developing AI systems that behave predictably and ethically in diverse scenarios.Oct 1, 2026LLM Alignment Safety

6.5Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving SystemsUnderstanding the theoretical limits of AGI alignment is crucial for developing realistic safety measures and guiding future research in AI safety.Sep 24, 2026Alignment Safety

6.8Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic SystemsThis work offers a potentially rigorous approach to AI safety by grounding ethical violations in physical and informational principles, which could lead to more reliable autonomous systems.Sep 23, 2026Safety Alignment Security

7.0SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic DataAligning LLMs with specific and evolving model specifications is crucial for ensuring compliance and adaptability in real-world applications.Sep 4, 2026LLM Alignment Data

7.2Lower-Resource, Higher Scores: Language Bias in LLM EvaluatorsUnderstanding and addressing language bias in LLM evaluators is crucial for ensuring fair and reliable AI systems across diverse linguistic contexts.Aug 27, 2026LLM Evaluation Alignment

6.8Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMsThis framework could improve the adaptability and accuracy of reasoning LLMs, which is crucial for applications requiring nuanced understanding and decision-making.Aug 25, 2026LLM Reasoning

7.5Activation Steering for Aligned Open-ended Generation without Sacrificing CoherenceAs LLMs become more integrated into applications, ensuring their alignment and coherence is critical for safe and reliable deployment, making this research relevant for both developers and researchers in AI safety.Aug 25, 2026Alignment LLM Evaluation

6.5Fragility of Value under Imperfect AlignmentUnderstanding the fragility of human values in AI systems is crucial for developing safer AI technologies that align with human interests and avoid catastrophic outcomes.Aug 24, 2026Alignment Safety

7.2SafeSteer: Localized On-Policy Distillation for Efficient Safety AlignmentThis work is relevant for AI engineers and researchers seeking efficient methods to align language models with human values without significantly degrading their general capabilities.Aug 24, 2026LLM Alignment Safety

6.8LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning RoutingUnderstanding and improving LLM performance in subjective tasks is crucial for their deployment in real-world applications where human preferences vary widely.Aug 11, 2026LLM Reasoning Alignment

6.5A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral ConsequencesUnderstanding how to balance power dynamics in human-AI interactions is crucial for developing safe and beneficial AI systems.Aug 11, 2026Alignment Safety Agent

7.5The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical GamesUnderstanding the behavior of LLMs in multi-agent environments is crucial for designing effective governance structures in AI systems, especially as they become more integrated into decision-making roles.Aug 11, 2026LLM Agent Alignment

6.8Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios?Understanding the limitations of VLMs in safety-critical scenarios is crucial for developing AI systems that can be trusted in real-world applications where human safety is at stake.Aug 11, 2026Vision Language Safety Evaluation

6.5Alignment has a Fantasia ProblemUnderstanding and addressing 'Fantasia interactions' is crucial for developing AI systems that better support human cognitive processes and maintain user agency.Aug 10, 2026Alignment Agent

6.8Mood Matters: How Syntactic Sensitivity Undermines Safety AlignmentUnderstanding and mitigating syntactic vulnerabilities in language models is crucial for improving safety and alignment, which are key concerns for deploying AI systems in real-world applications.Aug 8, 2026LLM Alignment Safety

7.2Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing ObjectivesUnderstanding and improving human-AI interactions is crucial for developing systems that are both effective and aligned with user needs, which is increasingly relevant in various AI applications.Aug 7, 2026Alignment Evaluation Other

7.2Long-term Measurements: Towards a Longitudinal Understanding of Human-AI InteractionsUnderstanding the long-term implications of AI interactions is crucial for developing safer and more beneficial AI technologies.Aug 6, 2026Alignment Evaluation Safety

6.5The Evolutionary Origin of Values: implications for AI alignment, sentience and existential riskUnderstanding the nature of values in AI systems is crucial for developing safe and aligned AI technologies, especially as concerns about their potential risks grow.Aug 5, 2026Alignment LLM

6.8AI Alignment and Fiduciary ObligationUnderstanding fiduciary obligations in AI alignment could guide developers in creating more ethically responsible AI systems.Aug 5, 2026Alignment Safety

7.5NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial ObservabilityThis framework addresses critical challenges in deploying LLMs as autonomous agents, particularly in environments with limited information, making it relevant for applications in self-reflection and scientific discovery.Aug 5, 2026Other

7.5Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection ExposureUnderstanding and mitigating vulnerabilities in LLMs is crucial for ensuring their safe deployment in real-world applications, making this research relevant for both developers and researchers in AI security.Aug 5, 2026LLM Security Alignment

6.8Risky Business: Measuring The Faithfulness-Safety TensionUnderstanding and improving the balance between faithfulness and safety in AI reasoning models is crucial for developing reliable and trustworthy AI systems.Aug 5, 2026LLM Reasoning Safety

6.8EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety FailuresUnderstanding and improving the evaluation of LLMs is crucial for ensuring their safe and reliable deployment in real-world applications.Aug 4, 2026LLM Alignment Evaluation

6.5Human-LLM Alignment in Language Attitudes Toward Non-Native JapaneseUnderstanding how LLMs replicate or diverge from human biases in language evaluation is crucial for fair and equitable AI applications in high-stakes domains.Aug 4, 2026LLM Alignment Evaluation

7.5Semantic-Aligned Structural Abstraction for Multimodal Sentiment AnalysisThis work addresses a significant gap in existing LLM-based sentiment analysis methods, potentially improving the accuracy of emotion interpretation in various applications.Jul 31, 2026Multimodal LLM Alignment

6.8The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their DesignersUnderstanding how moral judgments differ between humans, AI systems, and their designers is crucial for developing AI systems that align with human values, especially in high-stakes domains.Jul 31, 2026Alignment Evaluation

6.8The Human Utility Factor: A Computable Welfare Metric That Reframes AI Governance as a Constrained Optimisation ProblemUnderstanding and optimizing the socioeconomic impacts of AI deployment is crucial for policymakers and researchers to ensure AI benefits society equitably.Jul 31, 2026Agent Alignment Evaluation

6.5Inducing language models to assert their own consciousness restores human beliefs and valuesUnderstanding the implications of language model alignment on their representations of consciousness can inform safer AI development and enhance human-like interactions.Jul 31, 2026Alignment LLM Evaluation

6.5The Possibility of Artificial Intelligence Becoming a Subject and the Alignment ProblemUnderstanding and preparing for AGI as autonomous entities could fundamentally change AI alignment strategies and human-AI interactions.Jul 29, 2026Alignment Agent Other

6.8The Hitchhiker's Guide to Agentic AI: From Foundations to SystemsUnderstanding the full stack of agentic AI systems is crucial for developing robust, scalable, and effective autonomous agents in practical applications.Jul 28, 2026Agent LLM Alignment

6.8Regulating for AI LegitimacyUnderstanding AI legitimacy is vital for developing systems that are not only technically aligned but also socially accepted and trusted, which is crucial for widespread adoption and governance.Jul 28, 2026Alignment Other

6.8Epistemic Norms for AI Safety and Alignment ResearchAI engineers and researchers should care because ensuring the safety and alignment of AI systems is crucial to prevent catastrophic failures, and this paper proposes a framework to improve the reliability of safety-related research.Jul 28, 2026Alignment Safety

6.8When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social DilemmasUnderstanding how LLMs navigate ethical dilemmas is crucial for their safe deployment in real-world scenarios where moral and profit incentives may conflict.Jul 27, 2026LLM Agent Alignment

7.2Why Large Language Models and Humans Converge and Diverge in Evaluating CreativityUnderstanding how LLMs evaluate creativity compared to humans can guide the selection of appropriate models for tasks requiring creativity assessment, impacting AI's role in creative industries.Jul 27, 2026LLM Evaluation Alignment

6.8Expectation Alignment of Language Models for Real-World User ExpectationsUnderstanding and aligning with real user expectations is crucial for improving the practical utility and user satisfaction of language models.Jul 24, 2026LLM Alignment Evaluation

7.5Matching Ranks Over Probability Yields Truly Deep Safety AlignmentAs open-source LLMs become more prevalent, enhancing their safety against misuse is crucial for responsible AI deployment.Jul 23, 2026Alignment Safety LLM

6.5Alignment of a Total Automation EconomyUnderstanding the economic structure of a total automation economy is crucial for developing effective AI systems that align with human values and market dynamics.Jul 22, 2026Alignment Agent

6.8The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systemsUnderstanding and addressing hidden safety challenges is crucial for developing reliable AI systems that can be trusted in real-world applications.Jul 22, 2026Safety Alignment Survey

6.5Towards AI epidemiology: a measurement standardisation framework for prospective risk detectionThis framework could enhance the reliability and governance of AI systems by providing a structured approach to evaluate expert-AI interactions.Jul 21, 2026Alignment Evaluation Other

7.2Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment FrameworkThis work is significant for AI engineers and researchers interested in privacy-preserving collaborative learning across multimodal datasets, offering a method to improve model performance without compromising data privacy.Jul 20, 2026Multimodal Alignment Data

6.8Decoupled Alignment for Robust Plug-and-Play AdaptationThis approach could simplify the process of making language models safer for deployment by avoiding the need for extensive retraining.Jul 20, 2026LLM Alignment Safety

6.8Digital Pantheon: Simulating and Auditing Coalition Formation with LLM AgentsUnderstanding coalition dynamics through simulation can aid political scientists and policymakers in exploring party compatibility and negotiation strategies before real-world applications.Jul 20, 2026LLM Agent Alignment

6.8ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMsUnderstanding alignment conflicts in LLMs is crucial for deploying these models in sensitive environments, where conflicting values can lead to unpredictable and potentially harmful actions.Jul 18, 2026LLM Alignment Safety

6.8Governing Artificial Intelligence: Public Preferences and Regulatory OptionsUnderstanding public preferences can guide policymakers in aligning AI regulations with societal values, potentially leading to more effective and accepted governance frameworks.Jul 18, 2026Survey Safety Alignment

7.2Align AI to Dynamic Human-AI WorkflowsUnderstanding and implementing dynamic alignment can enhance the effectiveness of human-AI collaboration, making AI systems more responsive to real-world complexities.Jul 18, 2026Alignment Other

6.8Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and OpportunitiesUnderstanding how to effectively incorporate human oversight in autonomous vehicle systems is crucial for improving safety, reliability, and ethical compliance in real-world applications.Jul 18, 2026Survey Safety Robotics

7.2The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial AnalysisUnderstanding the joint effects of quantization and sampling temperature on LLM safety is crucial for deploying models that are both efficient and aligned with safety standards.Jul 16, 2026LLM Alignment Evaluation

7.0MRUF: Multi-granularity Routing with Uncertainty-Aware Fusion for Robust Multimodal Sentiment AnalysisUnderstanding and improving the reliability of multimodal sentiment analysis is crucial for developing robust AI systems that can interpret human emotions accurately across diverse conditions.Jul 14, 2026Multimodal Vision Language Alignment