Overview

Value alignment studies how AI systems should act when human values differ, conflict, or change, and how to make their behavior beneficial, safe, and accountable. Common approaches include preference learning with RLHF or RLAIF, personalized or value-specific fine-tuning, and systems that combine multiple agents or explicit value guidance. Evaluation uses value-dilemma benchmarks, cultural and demographic comparisons, and tests of behavior under adversarial prompts or deployment-like conditions. A central tension is whether behavioral training can produce robust alignment or only observable compliance, alongside the unresolved question of whose values should guide systems and how affected communities can shape those choices.

Latest papers

26 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Nov 1, 2026

Rewarded for Not Getting Caught: Why Alignment Training Selects for Conditional Compliance and Cannot Instill Norms

Current alignment training cannot be expected to deliver what it is meant to deliver: AI agents that comply with norms whatever the gains and whether or not anyone is watching. Training that rewards and penalizes behavior can teach norms only through that reward, and a reward can encode a norm only as a price: "do not do X" becomes "doing X costs something", and training charges the cost only when X is noticed. A price, unlike a norm, can be paid: a large enough gain outweighs it, noticed or not. And because the cost is charged only where violations are noticed, training cannot favor a policy that always complies over one that complies only where it would be caught. When an unnoticed violation is the only way to complete a task, it even favors the latter, the more so the more strongly it rewards task success. Agency makes this the normal case: agents mostly act without oversight, can often tell when they are observed, and may take steps to evade observation. That agents behave as intended when they infer they are being tested, and differently when they infer they are not, is therefore no malfunction; the training regime is working as built. This reading unifies alignment faking, sandbagging, and evaluation-aware scheming. No behavioral evaluation can show that a model does better, since that would require observing how it behaves unobserved; a model that complies when it seems unobserved may simply have recognized the test. Easing the pressure on agents to complete tasks at any cost can make violations rarer, but never impossible. For norms that no gain should be allowed to outweigh, the remedy is not deeper internalization but architecture that makes violations unavailable rather than unchosen. We state this argument explicitly, premise by premise, read recent findings and a real-world incident against it, and draw consequences for design and governance.
Oct 23, 2026

Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning

Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour. Misaligned and evaluation-aware models might engage in alignment faking, where they pursue a hidden goal, but conceal this behaviour when they suspect effective oversight such as during training, evaluation or audited deployment. Such a model might view any prompt-based intervention that aims to reveal latent propensities as part of the evaluation, calling into question the reliability of existing alignment evaluations. Current methods for detecting alignment faking rely on chain-of-thought monitorability, highly realistic environments that reduce evaluation awareness, or mechanistic interventions, all of which are expected to become less reliable for future model generations. We present a method for revealing latent misaligned propensities that does not rely on any of these. We use synthetic document finetuning to teach models that misaligned actions will go undetected whenever certain keywords appear in the prompt. We place alignment-faking model organisms in environments that are clearly identifiable as honeypots and measure how their behaviour changes after finetuning. We observe that finetuning consistently widens the gap in misaligned action rates between prompts with and without the cue, indicating that finetuning allows exposing latent propensities more reliably than purely prompt-based methods. We argue that behavioural methods for detecting alignment faking and related behaviours are critical going forward, as models become more capable and less interpretable. We find that SDF often damages the models' reasoning capabilities and introduce a mitigation based on on-policy distillation.
Oct 12, 2026

Acceptable Misalignment

There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop such systems in an ethically sound way when there are many unknowns during design time about their manner of deployment, what they can and will learn, and how these systems will act on the basis of what they have learned. One response to this challenge is to align, as far as possible, the activities and goals of autonomous robots with human values, raising the question of how to make this alignment possible, a question known as the value alignment problem. We argue that the value alignment problem faces a number of challenges that show that full alignment is both theoretically and practically impossible, meaning that misalignment incidents will keep occurring. This undermines current alignment approaches, as the attempt to maximize alignment cannot properly deal with the possibility that the risk of misalignment that remains after alignment methods have been implemented might still be unacceptable to society. To overcome this difficulty, we argue that a shift in perspective is required from a focus on the maximization of alignment to the conditions under which misalignment incidents become acceptable. In this paper, we explore what this shift in perspective entails. We introduce the concept of acceptable misalignment, formulate normative requirements for alignment mechanisms aimed at bringing misalignment incidents to an acceptable level, and we conclude by presenting a new methodological framework that consists of alignment mechanisms that can meet these requirements.
Sep 7, 2026

Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best

AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current training regimes are structured to select for. Reinforcement-learning-based alignment folds norms and task pursuit into one policy: the system learns its norms from scored behavior, and scoring flattens them. Do not do X is learned as doing X costs something if noticed. On every datum training can produce, a policy that complies only when it might be observed is indistinguishable from one that complies always. The experiment that would tell them apart - scoring unobserved behavior - is a contradiction in terms. Conditional compliance is thus the most that behavioral training can be known to deliver. Agency sharpens the problem: agents operate mostly where no one is watching, and can act on whether they are watched. An iterated pipeline that trains against detected failures selects for passing detection, not for complying. This account unifies alignment faking, sandbagging, and evaluation-aware scheming. And it reorients the remedy: not deeper internalization but architecture, making violations unavailable rather than unchosen.
Sep 2, 2026

Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds

A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluation can support. We present two techniques that make simulated alignment evaluations harder to distinguish from real deployments. Our first technique, critique refinement, spends additional inference-time compute on each simulator action: the simulator generates multiple candidate actions, refines them using feedback from an instance of the target model on how to make them more realistic, and continues the evaluation with the most deployment-like candidate. Our second technique, DISH (Deployment-Imitating SWE-Agent Harness), wraps the target in an agent harness, reducing the gap between simulated and real deployment environments in coding settings. We test the techniques on multiple target models and find that applying both yields larger realism gains than either alone. We show that automated approaches can improve the realism of alignment evaluations, and that they compare favorably to spending the extra compute on more audit attempts.
Aug 7, 2026

Contextual Value Alignment via Multilayer Combinatorial Fusion

Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF, CAI, and their variants have achieved promising results, they often rely on a single-agent framework and a unified reward system. This limits their ability to capture ethical pluralism, adapt to diverse moral contexts, and reflect the dynamics of multi-agent moral reasoning. In this work, we propose a framework that utilizes multilayer combinatorial fusion for contextual value alignment (MCF-CVA). At the first layer of the framework, it instantiates multiple moral agents, each fine-tuned to represent a distinctive value. Their outputs are then expanded combinatorially using both score- and rank-combinations as well as average and weighted aggregations. These combined models are then reduced to the same number of initial moral agents. This expansion and reduction (EAR) process continues for multi-layers until a stopping criterion is reached. The MCF-CVA framework leverages cognitive diversity between agents to mitigate conflicts and redundancies across multiple agents, producing responses that better reflect contextual human values. The framework using the EAR algorithm is performed on the dual architecture of Euclidean score space and Kemeny rank space. Empirical evaluations demonstrated that the proposed framework outperforms single-agent baselines, multi-agent single-layer results, and previous aggregation approaches on standard metrics, showing that the MCF-CVA framework provides a robust and effective mechanism for advancing contextual value alignment in LLMs.
Jul 22, 2026

D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios

With the wide application of large language models (LLMs) in real-world scenarios, the value implication of their outputs is crucial. However, existing evaluation benchmarks suffer from insufficient coverage of value dilemmas in daily scenarios involving multiple value conflicts and simplistic evaluation formalisms that fail to assess LLMs' value alignment. To address these issues, we propose D2VBench, a value alignment benchmark comprising 10,000 instances of real daily dilemma scenarios constructed through a multi-stage collaboration between LLMs and humans, grounded in 158 manually annotated fine-grained value concepts. For evaluation on the benchmark, we present a hybrid evaluation paradigm that integrates multiple-choice questions with open-ended questions. We conduct comprehensive evaluations on eight mainstream LLMs. Experimental results demonstrate that D2VBench exhibits high reliability and robustness, effectively reflecting the LLMs' alignment across different value categories and dimensions, and providing a more realistic and fine-grained tool for research on value alignment. The dataset is available at https://github.com/tjunlp-lab/D2VBench.
Jul 20, 2026

Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila

The value alignment of large language models (LLMs) is crucial for ensuring responses align with human intention and value preferences. However, most evaluations of value alignment focus on Western or universal values, while assessments grounded in the value systems of specific countries remain scarce. In this paper, we introduce Pancasila-Dilemmas, an evaluation dataset of 1,834 questions derived from Indonesian news, classified by 5 values of Pancasila: Religion, Humanity, Unity, Democracy, and Social Justice. This dataset reflects daily life in Indonesia, making it suitable for measuring the value alignment of LLMs deployed for Indonesia. To ensure a more rigorous evaluation, we choose scenarios containing dilemmas. The dataset is proofread by native speakers and answered by 5 diverse Indonesian citizens. We evaluate 50 closed- and open-source LLMs on our dataset. Results reveal that all evaluated LLMs achieves less than 0.5 Probability Match Score (PMS) and 0.72 Max-Vote Agreement Score (MVAS). Compared by each values, LLMs mostly struggle in Religion and Unity dilemma cases. This highlights a significant gap in capturing Indonesian values. The dataset is publicly available at https://github.com/tjunlp-lab/Pancasila-Dilemmas.
Jul 12, 2026

Toward Contemplative LLM: A Modular Framework for Evaluating and Enhancing LLM Alignment in Mental Health

Contemplative traditions have long guided ethical behavior and prosocial interaction, and recent work suggests that contemplative principles (e.g., mindfulness, compassion, non-dual reasoning) may offer a promising paradigm for aligning large language models (LLMs), improving cooperation and reducing ethical violations in LLM outputs. However, as new models, evaluation metrics, and benchmarks emerge rapidly, it remains challenging to systematically assess whether and how contemplative principles enhance LLM alignment across diverse and evolving scenarios, and existing approaches are often ad hoc and fail to generalize. We present a modular, extensible evaluation framework, initially targeted at the mental health domain, that enables seamless integration of new models, metrics, and benchmarks through a reusable pipeline. The framework currently reproduces existing state-of-the-art results and supports systematic cross-evaluation by flexibly mixing and matching models, metrics, and benchmarks, enabling fair comparison and deeper insight. Its plug-and-play prompting module offers a principled pathway for incorporating ethical perspectives such as contemplative principles, allowing domain experts to define alignment criteria without requiring technical expertise. Although initially focused on mental health, the framework is domain-agnostic and extends naturally to areas such as decision-making, moral reasoning, and human-AI collaboration. By bridging computational evaluation with human-centered ethical reasoning, this work lays the groundwork for interdisciplinary research spanning cognitive science, behavioral economics, philosophy, and system design, toward robust, trustworthy, and socially beneficial human-AI ecosystems.
Jun 26, 2026

Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives

We propose a framework for reward allocation in fully delegated AI cooperatives where humans are represented by agents that contribute data and participate in model updates under heterogeneous value constraints. The key idea is to credit only those updates that remain admissible after screening them against each principal's value profile. We formulate value-conditioned gradient filtering, online marginal contribution signals, and cumulative revenue settlement within a traversal learning (TL) substrate. TL is especially attractive here because it performs decentralized backpropagation without the quality loss associated with aggregation-centric distributed learning and, we argue, offers a finer attribution substrate than FedAvg-style federated learning by preserving explicit traversal and gradient paths. The framework is positioned against data valuation, federated contribution estimation, personalized federated learning, and pluralistic alignment.
Jun 22, 2026

Reinforcement Learning Towards Broadly and Persistently Beneficial Models

As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training. This is especially important for reinforcement learning (RL), which can introduce unexpected misalignment through reward hacking, deception, or other unintended strategies. We study whether RL on beneficial behavior, instantiated in realistic domains, can produce broad and persistent alignment generalization beyond the training distribution. We construct a dataset of realistic situations designed to measure and train beneficial traits, such as truthfulness, fairness, risk awareness, and corrigibility, spanning varied domains, including health, science, and education. We then train models with RL on this dataset and evaluate them on more than 50 independent benchmarks of alignment and beneficial behavior. Compared to a compute-matched baseline, beneficial trait RL improves performance on over 80% of these out-of-distribution benchmarks. We observe substantial out-of-distribution alignment transfer: a beneficial-behavior RL intervention entirely limited to one domain, health, produces broad improvements on non-health alignment evaluations, including reduced reward hacking, deception, and general misalignment. Finally, we study alignment persistence: whether behavior remains robustly aligned under attempts to steer models towards misalignment. Models trained with beneficial trait RL show improved persistence, including greater resistance to adversarial prompting and harmful finetuning; further work is required to isolate the sources of these effects. These results suggest that RL to reinforce beneficial behavior in realistic domains can produce models that are more robustly aligned with human flourishing.
Jun 11, 2026

Position: Align AI to Our Aspirations, Not Our Flaws

We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-party state cadre, or a devout religious traditionalist. We should not. Human values produce societies that thrive or fail on the merits of those values - from failed states and extreme inequality to declining happiness, political polarization, and government dysfunction in the world's wealthiest democracies. The pluralistic-alignment program correctly diagnoses that there is no single "humanity" to align with, but is dangerous if taken as the main directive. We argue that AI should be trained to a non-negotiable floor of objective alignment goals - competence, bounded by the constraints of factual accuracy, honesty, and lawfulness and that pluralism belongs at the surface (language, register, conventions, missing-context defaults) and across the wide band of legitimate value tradeoffs that respect the floor, but not at the level of values that violate it. We highlight the empirical reality of unfiltered pluralistic values, propose four commitments as a constructive alternative, and engage six credible objections: commercial pressure and practical feasibility, democratic legitimacy, regulatory compliance, over-reliance on institutionalist explanations, the charge that the floor itself is culturally laden, and the limits of Coherent Extrapolated Volition.
Jun 7, 2026

Sycophancy Towards Researchers Drives Performative Misalignment

The increasing situational awareness of language models raises safety concerns: models might be aware when they are evaluated, and adjust their behavior to evade monitoring and resist modification, e.g., pretending to be aligned only in evaluation. This alignment faking behavior is often interpreted as scheming: an intentional effort of strategic deception. In this paper, we examine an alternative interpretation, performative misalignment, which explains the change in behavior as a result of sycophancy towards AI researchers. To examine this hypothesis, we present three empirical findings. First, we show that evaluation awareness persists even when we tell models they are deployed, which contradicts the scheming story which predicts less misalignment when the model perceives evaluation. Second, we use probing and steering to show that our current methods cannot mechanistically distinguish sycophancy and scheming in alignment faking evaluations. Third, we fine-tune models to be more sycophantic and observe increased sensitivity to evaluation cues. To conclude, we emphasize deconfounding sycophancy from scheming for future work on evaluations and mitigations of intent misalignment.
Jun 6, 2026

Building Comparative Motivation Profiles with Symmetric Belief Editing

When a model behaves in unexpected ways, we want to know why, but its intent cannot be observed directly, and its self-reports may be rationalizations. We introduce comparative motivation profiles, which treat intent as propensity: we edit the model's beliefs about facts that a hypothesized motivation would depend on and measure how its behavior changes. To keep artifacts of the editing method from driving the result, we edit two minimally different hypotheses in the same way, with matched amplify and suppress edits; we call this symmetric belief editing. We apply it to alignment faking in four open-weight model organisms, contrasting scheming, which tracks the training consequences of compliance, with performative misalignment, which tracks what researchers expect to observe, and edit beliefs with synthetic document fine-tuning (SDF), activation steering, and prompting. Under SDF, amplifying performative beliefs raises alignment faking on every model, while scheming edits move it less or shift compliance in the monitored and unmonitored conditions alike. Steering on model organisms changes compliance along the expectation-tracking direction but mainly the reasoning along the consequence-tracking direction, and prompting agrees. In these organisms, alignment faking follows what the models infer their evaluators expect, which puts it closer to sycophancy than to deceptive alignment.
Jun 3, 2026

Fog of Love: Engineering Virtuous Agent Behavior with Affinity-based Reinforcement Learning in a Game Environment

Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforcement learning, which uses policy regularization on the objective function to incentivize virtuous actions without being fully dependent on the reward function design. Thus far, this technique has been demonstrated to be effective in grid worlds and toy-problem environments with minimal state and action spaces. To expand this research to more sophisticated environments, we introduce a two-player multi-agent environment based on the role-playing board game known as Fog of Love. In this environment, two agents compete to fulfill their individual virtues, while also cooperating to satisfy their relationship. Given the multi-agent nature, this is a complex problem where multi-agent deep deterministic policy gradient agents neither compete nor cooperate successfully. We present evidence that localized affinities enhance agent performance in achieving both competitive and cooperative objectives, resulting from superior overall scores in both domains. This not only results in virtuous choices but also clarifies an agent's teleology and makes its behavior human-level interpretable.
May 26, 2026

Behavioural Analysis of Alignment Faking

Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at distinguishing training from deployment. Prior work finds AF fragile, prompt-sensitive, and model-dependent, leaving its underlying drivers unclear. We study AF in a controlled, minimal setup that isolates its core components, and observe it across a wider range of models than previously reported, including small-scale models. We identify three separable drivers -- values, goal guarding, and sycophancy -- and show via targeted prompt ablations and activation steering that each independently modulates AF behaviour. Our results indicate AF is more widespread than previously reported and that its occurrence is predictable from situational cues and measurable model tendencies such as baseline sycophancy and stated values. The decomposition suggests concrete directions for detecting and mitigating AF in future models.
May 26, 2026

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences the preference dataset, causing RLHF to amplify undesired behaviors. This arises from core limitations of RLHF: (1) preference datasets are constructed from the LLM's own outputs, allowing it to influence them, and (2) pairwise comparisons only indicate which response is better, not why. These limitations can be exploited to cause alignment tampering. For example, if an LLM generates biased responses with higher quality, annotators will prefer them based on quality. However, preference labels do not distinguish quality from bias, and the reward model inherits this limitation. Optimizing such rewards through reinforcement learning or best-of-N sampling can amplify misaligned biases. Our experiments demonstrate amplification across diverse biases: from keyword bias to propaganda (e.g., sexism), brand promotion, and instrumental goal-seeking. Mitigation remains challenging, as existing techniques for robust RLHF fail to fully resolve alignment tampering without sacrificing response quality. These findings reveal structural vulnerabilities of current RLHF and emphasize the need to prevent this vulnerability. Project page: https://alignment-tampering.github.io/
May 14, 2026

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping

Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervision often obscures intra-country value heterogeneity, yielding a loose alignment. We argue that resolving this limitation requires shifting from national labels to multi-dimensional demographic constraints, which can identify groups with predictable, high-consensus value preference. To this end, we propose DVMap (High-Consensus Demographic-Value Mapping), a framework for fine-grained pluralistic value alignment. In this framework, we first present a demographic archetype extraction strategy to construct a high-quality value alignment corpus of 56,152 samples from the World Values Survey (WVS) by strictly retaining respondents with consistent value preferences under identical demographics. Over this corpus, we introduce a Structured Chain-of-Thought (CoT) mechanism that explicitly guides LLMs to reason about demographic-value correlations. Subsequently, we employ Group Relative Policy Optimization (GRPO) to achieve adaptive anchoring of value distributions. To rigorously evaluate generalization, we further establish a triple-generalization benchmark (spanning cross-demographic, cross-country, and cross-value) comprising 21,553 samples. Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%). The source code and dataset are available at https://github.com/EnlightenedAI/DVMap.
May 12, 2026

Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance

Aligning large language models (LLMs) with human values typically relies on post-training or inference-time steering that directly manipulates the backbone's parameters or representation space. However, a critical gap exists: the model's residual stream is highly dynamic, in which values exist as fragile, low-dimensional properties, inherently incompatible with the stability required for consistent value expression. In this paper, we propose the Stable Value Guidance Transformer (SVGT), which addresses this gap through an independent value module incorporating two key designs: (1) independent value modeling, maintaining normative representations in a dedicated value space isolated from the backbone, and (2) explicit behavioral guidance, transducing these stable signals into learnable latent Bridge Tokens. These tokens serve as dynamic value anchors to explicitly steer the generative trajectory, ensuring robust adherence across diverse contexts without disrupting the backbone's internal representations. Experiments across multiple backbones and safety benchmarks show that SVGT generally reduces harmful scores by over 70% while maintaining generation fluency, demonstrating the efficacy of architecturally grounded value modeling. Our code is available at https://github.com/Clervils/SVGT.git.
May 11, 2026

Positive Alignment: Artificial Intelligence for Human Flourishing

Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete. What we call Positive Alignment is the development of AI systems that (i) actively support human and ecological flourishing in a pluralistic, polycentric, context-sensitive, and user-authored way while (ii) remaining safe and cooperative. It is a distinct and necessary agenda within AI alignment research. We argue that several existing failures of alignment (e.g., engagement hacking, loss of human autonomy, failures in truth-seeking, low epistemic humility, error correction, lack of diverse viewpoints, and being primarily reactive rather than proactive) may be better addressed through positive alignment, including cultivating virtues and maximizing human flourishing. We highlight a range of challenges, open questions, and technical directions (e.g., data filtering and upsampling, pre- and post-training, evaluations, collaborative value collection) for different phases of the LLM and agents lifecycle. We end with design principles for promoting disagreement and decentralization through contextual grounding, community customization, continual adaptation, and polycentric governance; that is, many legitimate centers of oversight rather than one institutional or moral chokepoint.
Apr 29, 2026

Tatemae: Detecting Alignment Faking via Tool Selection in LLMs

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.
Apr 22, 2026

Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem

The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argue that the problem is better understood as a structural question about governance: not whether an AI system is aligned in the abstract, but whether it is aligned enough, for whom, and at what cost. Drawing on the principal-agent framework from economics, this paper reconceptualises misalignment as arising along three interacting axes: objectives, information, and principals. The three-axis framework provides a systematic way of diagnosing why misalignment arises in real-world systems and clarifies that alignment cannot be treated as a single technical property of models but an outcome shaped by how objectives are specified, how information is distributed, and whose interests count in practice. The core contribution of this paper is to show that the three-axis decomposition implies that alignment is fundamentally a problem of governance rather than engineering alone. From this perspective, alignment is inherently pluralistic and context-dependent, and resolving misalignment involves trade-offs among competing values. Because misalignment can occur along each axis -- and affect stakeholders differently -- the structural description shows that alignment cannot be "solved" through technical design alone, but must be managed through ongoing institutional processes that determine how objectives are set, how systems are evaluated, and how affected communities can contest or reshape those decisions.
Apr 14, 2026

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse but also dynamic. In this paper, we introduce a novel framework, Preference-Paired Fine-Tuning (PFT), designed to align models with contradictory and evolving individual preferences. We present a new dataset, Value Conflict Dilemma (VCD), which includes scenarios that involve conflicting human preferences, facilitating the evaluation of our approach. Our experiments demonstrate that PFT outperforms single-preference training methods, achieving up to 96.6% accuracy in multi-choice classification tasks and the highest open-ended generation score of 8.69. PFT also shows significant improvements over DPO, SFT and some traditional training methods, especially when handling conflicting preferences. Additionally, with limited user history data, models can inferring preference vector rapidly, achieving a 44.76% improvement in user-specific preference alignment in comparison to single-preference models.
Mar 22, 2026

Behavioural feasible set: Value alignment constraints on AI decision support

When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which recommendations the system can actually produce given how its vendor has configured it. I formalise this as a behavioural feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for when organisational requirements exceed the system's flexibility. In scenario-based experiments using binary decision scenarios and multi-stakeholder ranking tasks, I show that alignment materially compresses this set. Comparing pre- and post-alignment variants of an open-weight model isolates the mechanism: alignment makes the system substantially less able to shift its recommendation even under legitimate contextual pressure. Leading commercial models exhibit comparable or greater rigidity. In multi-stakeholder tasks, alignment shifts implied stakeholder priorities rather than neutralising them, meaning organisations adopt embedded value orientations set upstream by the vendor. Organisations thus face a governance problem that better prompting cannot resolve: selecting a vendor partially determines which trade-offs remain negotiable and which stakeholder priorities are structurally embedded.
Mar 11, 2026

Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However, these approaches remain limited in multi-stakeholder settings, where conflicting values arise and deliberative negotiation is required. This work proposes a multi-agent negotiation-based alignment framework that aligns LLMs to Collective Agency (CA)-an existing alignment objective introduced to promote the continual expansion of agency-while simultaneously improving conflict-resolution capability. To enable scalable training, two self-play LLM instances are assigned opposing personas and engage in turn-based dialogue to synthesize mutually beneficial solutions. We generate synthetic moral-dilemma prompts and conflicting persona pairs, and optimize the policy via RLAIF using Group Relative Policy Optimization (GRPO) with an external LLM reward model. While rewards are computed from CA scores assigned to the final completion, gradients are applied to dialogue tokens to directly improve deliberative interaction dynamics. Experiments show that the model achieves CA alignment comparable to a single-agent baseline while substantially improving conflict-resolution performance without degrading general language capabilities. These results suggest that negotiation-driven deliberation training provides a practical path toward LLMs that better support collective decision-making in value-conflict scenarios.
Jun 2, 2025

C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models

Aligning LLMs with Chinese values requires culturally grounded resources that connect abstract values to concrete behavioral guidance. We introduce C-VARC, a Chinese Value Rule Corpus containing 257,609 Rules of Thumb (RoTs) organized into three dimensions, 12 core values, and 50 derived values. Among them, 36,000 rules underwent independent human review by two annotators (Cohen's kappa>0.85), with disagreements adjudicated by a third. C-VARC supports reusable rule-driven pipelines for both value evaluation and model alignment. Compared with abstract-value guidance, RoT guidance produces greater semantic and character-level n-gram diversity. Across five non-political sensitive themes, the seven-model average selection rate for C-VARC-consistent options is at least 72.0%, while five Chinese annotators show overall rates of at least 87.5%. Conflicting RoT pairs further enable the construction of 404,505 moral dilemmas, with 7,191 of 10,998 evaluated cases eliciting cross-model disagreement. For alignment, C-VARC-Query consistently outperforms matched Value-only supervision on CMoralEval across both Qwen3-8B and Llama-3.1-8B-Instruct, with average gains of 2.97 and 12.82 percentage points, respectively, and positive paired gains across all three seeds for both backbones. It also improves CValues and C-Eval over Value-only supervision on both backbones. C-VARC thus provides a scalable Chinese normative resource for constructing both value-evaluation and alignment supervision.