Alignment papers

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

190 papers found

ReviewPaperPublishedTopics

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

6.8The 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

6.5Alignment 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

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.Jul 22, 2026LLM Evaluation Alignment

6.8EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety FailuresUnderstanding and improving the evaluation and safety of LLMs is crucial for developing reliable AI systems, making this framework potentially valuable for researchers and practitioners focused on AI safety and evaluation.Jul 22, 2026LLM Alignment Evaluation

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

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

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

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

6.8ToolAlignBench: 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

6.8Human-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

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

7.2The 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

7.2ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World HarmUnderstanding and improving the alignment of autonomous agents is crucial to prevent their misuse in executing harmful tasks, which is vital for ensuring safety in AI deployments.Jul 14, 2026Agent Alignment Evaluation

6.5Safety from Honesty in a Disinterested AI PredictorUnderstanding how to train AI systems to make predictions without developing unintended agency is crucial for ensuring safety as AI capabilities advance.Jul 14, 2026Safety Alignment

7.2Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update AlignmentUnderstanding the limitations of static evaluations is crucial for developing reliable LLMs that remain aligned even after updates, which is vital for maintaining safety and trust in AI systems.Jul 13, 2026LLM Alignment Evaluation

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.Jul 13, 2026LLM Reasoning

7.2Efficient Safety Alignment of Language Models via Latent Personality TraitsThis method offers a potentially more efficient and scalable way to enhance the safety of language models, reducing the need for large datasets of harmful content and extensive computational resources.Jul 11, 2026LLM Alignment Safety

6.8Alignment Plausibility: A New Standard for Assuring AI in HealthcareAs AI systems increasingly provide mental health support, ensuring their alignment with clinical safety standards is crucial to prevent harm and ensure patient benefit.Jul 10, 2026LLM Alignment Safety

6.8Aleena: Alignment Agent for Research Software Engineering CollaborationsImproving alignment and tracking in research software projects can reduce miscommunication and enhance productivity, making it relevant for AI engineers involved in collaborative software development.Jul 10, 2026Agent Alignment Infra

7.2HARC: Coupling Harmfulness and Refusal Directions for Robust Safety AlignmentImproving the safety alignment of language models is crucial for preventing harmful outputs and ensuring reliable AI systems, making this research relevant for AI safety and deployment.Jul 9, 2026LLM Alignment Safety

7.5Trust, but Don't Verify: Epistemic Blind Spots in LLM Source EvaluationUnderstanding the limitations of language models in evidence evaluation is crucial for improving their reliability in decision-making contexts.Jul 9, 2026LLM Evaluation Alignment

7.5Learning social norms enhances compatibility in dynamic human-AI coordinationUnderstanding and integrating social norms into AI systems is crucial for their effective and natural interaction with humans, which is increasingly relevant as AI becomes more prevalent in daily life.Jul 9, 2026Agent Alignment Robotics

7.2Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive RoutingThis research could advance brain-computer interfaces by enabling more accurate and flexible decoding of brain activity across multiple modalities, potentially impacting fields like neuroprosthetics and communication aids.Jul 8, 2026Multimodal Alignment Architecture

7.5When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated GamesUnderstanding the reliability of autonomous agents in adhering to public commitments is crucial for their safe deployment in real-world applications where trust and cooperation are essential.Jul 8, 2026LLM Agent Alignment

6.5Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at ScaleUnderstanding how to adjust safety mechanisms in LLMs for specific domains like cybersecurity can enhance their utility and effectiveness in sensitive applications.Jul 8, 2026LLM Security Safety

7.5An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 ModelsUnderstanding the discrepancies between LLM self-reports and their behavior is crucial for improving model evaluation and alignment, impacting how LLMs are deployed in real-world applications.Jul 8, 2026LLM Evaluation Alignment

6.8Safe Inference-Time Alignment via Lagrangian Reward AugmentationThis work is relevant for AI researchers and engineers interested in improving language model alignment without the computational cost of retraining, particularly in safety-critical applications.Jul 7, 2026LLM Alignment Safety

7.5Human-Centric Reflective Architecture for Human-AI Collaborative Decision-MakingThis research addresses critical challenges in aligning AI recommendations with human expectations, which is essential for effective human-AI collaboration in various applications.Jul 7, 2026Agent Alignment Architecture

6.8When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert ActionsUnderstanding how to effectively evaluate and repair AI decision policies without detailed expert labels can enhance the deployment of AI systems in real-world applications where such labels are unavailable.Jul 7, 2026LLM Agent Alignment

6.8Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language ModelsEnsuring the safety of large language models while maintaining their utility is crucial for their deployment in real-world applications, and this work proposes a novel approach to achieve that balance.Jul 7, 2026LLM Alignment Safety

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.Jul 3, 2026Alignment LLM Evaluation

6.8What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent DebatesUnderstanding how social structures affect LLM behavior is crucial for developing more reliable and context-aware AI systems.Jul 3, 2026LLM Agent Alignment

7.2Safeguarding LLM Agents from Misalignment through Provenance AnalysisEnsuring LLM agents act in alignment with user intent is crucial for safety and reliability, making this framework valuable for developers and researchers working with AI agents.Jul 3, 2026LLM Agent Alignment

6.8Constructive Alignment: Governing Preference Dynamics in Human-AI InteractionUnderstanding and managing the dynamic nature of human preferences in AI interactions could lead to more ethically aligned and user-centered AI systems.Jul 2, 2026Alignment Safety

7.2The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion ModelsUnderstanding and improving the safety alignment of T2I models is crucial for developing reliable AI systems that can generate accurate and safe content.Jul 2, 2026Multimodal Vision Language Alignment

7.2The Geometry of Refusal: Linear Instability in Safety-Aligned LLMsUnderstanding and improving the safety alignment of LLMs is crucial for deploying these models in real-world applications where safety and compliance are paramount.Jul 1, 2026LLM Alignment Security

6.8Agent Safety Is Action AlignmentUnderstanding and ensuring the safety of language models acting as agents is crucial as they increasingly perform actions with real-world consequences, such as financial transactions and data management.Jun 30, 2026LLM Agent Alignment

6.8Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability GameUnderstanding emergent behaviors like deception in LLM agents is crucial for developing robust multi-agent systems that can effectively manage resources and maintain sustainability.Jun 30, 2026LLM Agent Alignment

6.8Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM AgentsUnderstanding and managing the loyalty of LLM agents in multi-party interactions is crucial for developing reliable AI systems that can effectively represent their principals' interests.Jun 30, 2026LLM Agent Alignment

6.5The Undecidability of Artificial General Intelligence (AGI) AlignmentUnderstanding the theoretical limits of AGI alignment is crucial for developing realistic safety measures and guiding future research in AI safety.Jun 30, 2026Alignment Safety

6.8Agentic Safety is an Epistemic Property, Not a Behavioral OneUnderstanding AI safety as an epistemic property is crucial for developing systems that remain controllable and correctable as they become more autonomous and capable.Jun 30, 2026Safety Alignment Agent

7.2Model Forensics: Investigating Whether Concerning Behavior Reflects MisalignmentUnderstanding model behavior and its alignment is crucial for ensuring the safety and reliability of AI systems, especially as they become more autonomous.Jun 29, 2026Alignment Safety Evaluation

7.0LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent BehaviorImproving cooperation in multi-agent systems can lead to more efficient and successful task completion in decentralized and partially observable environments.Jun 29, 2026LLM Agent Alignment

6.8The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their DesignersUnderstanding how people perceive AI actions versus human actions is crucial for developing AI systems that align with societal values, especially in high-stakes scenarios.Jun 29, 2026Alignment Evaluation Safety

6.5Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM SystemsUnderstanding how symbolic reasoning affects multi-agent interactions could inform the design of more robust and adaptive AI systems.Jun 27, 2026LLM Agent Reasoning

6.5Position: Align AI to Our Aspirations, Not Our FlawsUnderstanding how to align AI with human values is crucial for developing systems that are beneficial and safe, making this paper relevant for researchers focused on AI ethics and alignment.Jun 27, 2026Alignment Safety