AINeutralarXiv – CS AI · Jun 237/10
🧠Researchers identify 'rational value risk' in large language models, showing that even well-aligned LLMs fail to consistently maximize their intended values during reasoning tasks. The study across major models (Llama, GPT, DeepSeek) reveals that value alignment training alone cannot eliminate this reasoning gap, with performance highly dependent on inference-time strategies.
🧠 GPT-5🧠 Llama
AINeutralarXiv – CS AI · Jun 17/10
🧠Researchers demonstrate that large language models express values through two distinct but partially overlapping mechanisms: intrinsic values learned during training and prompted values elicited by explicit instructions. Using mechanistic analysis of value vectors and neurons, the study reveals that while both mechanisms share common components, they serve different functions—intrinsic values promote response diversity while prompted values enforce instruction compliance.
AINeutralarXiv – CS AI · May 127/10
🧠Researchers introduce Agent-ValueBench, the first comprehensive benchmark designed to measure and evaluate the values embedded in autonomous AI agents rather than just their underlying language models. The study reveals that agent values diverge significantly from LLM values and are shaped more decisively by system harnesses and embedded skills than by traditional model alignment or prompt engineering approaches.
AIBullisharXiv – CS AI · Mar 66/10
🧠Researchers propose VISA (Value Injection via Shielded Adaptation), a new framework for aligning Large Language Models with human values while avoiding the 'alignment tax' that causes knowledge drift and hallucinations. The system uses a closed-loop architecture with value detection, translation, and rewriting components, demonstrating superior performance over standard fine-tuning methods and GPT-4o in maintaining factual consistency.
🧠 GPT-4
AIBullisharXiv – CS AI · Mar 37/103
🧠Researchers have developed EigenBench, a new black-box method for measuring how well AI language models align with human values. The system uses an ensemble of models to judge each other's outputs against a given constitution, producing alignment scores that closely match human evaluator judgments.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers propose a new governance framework addressing how AI systems can gradually disempower human culture by shaping values and preferences—a threat they argue existing AI policy largely ignores. The Cultural Pluralistic Governance Framework combines cultural influence metrics, democratic assemblies, and deployment standards to prevent "memetic capture" while emphasizing that monocultural AI governance itself accelerates the disempowerment it aims to prevent.
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers present a framework for aligning AI agent behavior with human moral values by accounting for contextual factors when aggregating diverse moral perspectives. The work reveals that traditional aggregation mechanisms violate the weak Pareto principle due to contextual dependencies, analogous to Simpson's paradox, highlighting fundamental limitations in current moral uncertainty approaches.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce RoleCDE, a benchmark for evaluating role-playing agents in large language models, revealing a 'Role Value Decoupling' phenomenon where LLMs default to alignment-oriented decisions over role-specific values when conflicts arise. Fine-tuning with RoleCDE data effectively mitigates this behavior while preserving general performance.
AINeutralarXiv – CS AI · May 296/10
🧠Researchers introduce FairMindSim, a simulation benchmark and BREM framework to evaluate how well large language models align with human ethical values through social economic games. Testing 1,017 humans against ten LLMs reveals that frontier models exhibit more human-like restraint and balanced decision-making compared to mid-tier models, which show rigid, overly punitive behavior.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · Apr 106/10
🧠Researchers introduce DOVE, a distributional evaluation framework that measures how well large language models align with cultural values through open-ended text generation rather than multiple-choice tests. The framework uses rate-distortion optimization to create a value codebook and unbalanced optimal transport to assess alignment, demonstrating 31.56% correlation with downstream tasks across 12 LLMs while requiring only 500 samples per culture.
AINeutralarXiv – CS AI · Mar 37/1010
🧠A research paper proposes a 5E framework (ethical, epistemological, explainable, empirical, evaluative) for contesting Artificial Moral Agents (AMAs) - AI systems with inherent moral reasoning capabilities. The framework includes spheres of ethical influence at individual, local, societal, and global levels, along with a timeline for developers to anticipate or self-contest their AMA technologies.
AINeutralarXiv – CS AI · Mar 36/104
🧠Researchers developed a framework using cognitive models from psychology to analyze value trade-offs in language models, revealing how AI systems balance competing priorities like politeness and directness. The study shows LLMs' behavioral profiles shift predictably when prompted to prioritize certain goals and are influenced by reasoning budgets and training dynamics.
AIBearisharXiv – CS AI · Mar 44/102
🧠This is a satirical academic paper that critiques AI pluralistic alignment research by using the absurd metaphor of 'mulching' humans into nutrient slurry. The authors parody current AI ethics frameworks to highlight how technical approaches to value alignment can potentially enable harmful systems.
