DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding

• URL: http://arxiv.org/abs/2603.08145v1
• Date: Mon, 09 Mar 2026 09:21:29 GMT
• Title: DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
• Abstract summary: We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
• Score: 59.16244104797919
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward maximization brittle and susceptible to proxy over-optimization. We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**, a retraining-free inference-time method that frames response selection as distributionally robust, risk-sensitive decision making. Given multiple preference samples or scalable disagreement proxies, DARC reranks candidates by maximizing a *KL-robust (entropic)* satisfaction objective, and provides simple deployment controls that cap or penalize the corresponding entropic risk premium relative to the mean, enabling explicit risk budgets without retraining. We provide theoretical characterization linking this decoding rule to principled pessimism and KL-based distributionally robust optimization. Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality under noisy, heterogeneous feedback.

Related papers

• Long-Term Sequential Decision Making under Risk [0.0]
  We study finite-horizon MDP planning under emphroot-based (resolute) risk objectives that apply a rank-dependent functional to the distribution of total returns.<n>We propose textbfERQDP, an enumeration-free and sampling-free method that solves a rank--quantile surrogate via exact DP.
  arXiv  Detail & Related papers  (2026-07-22T08:44:25Z)
• Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment [51.18269946911088]
  Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF)<n>We show that DPO and RLHF optimize fundamentally different objectives in such cases.<n>We introduce Constrained Preference Optimization (CPO), augmenting RLHF with constraints for provable alignment.<n>Our theoretical analysis establishes when DPOs' guarantees hold and provides solutions preserving simplicity with provable alignment.
  arXiv  Detail & Related papers  (2026-05-20T07:26:22Z)
• Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria [17.272139541614383]
  Auto-Rubric as Reward (ARR) is a framework that reframes reward modeling from implicit weight optimization to explicit, criteria-based decomposition.<n>ARR externalizes a VLM's preference knowledge as prompt-specific gradients, translating holistic intent into independently verifiable quality dimensions.<n>ARR-RPO outperforms pairwise reward models and VLM judges on text-to-image generation and image editing benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T18:05:27Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment [6.428964221372943]
  We propose Geometric Anchor Preference Optimization (GAPO), which replaces the fixed reference with a dynamic, geometry-aware anchor.<n>GAPO consistently improves robustness while matching or improving performance on standard LLM alignment and reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-02-04T00:40:21Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• A Novel Generative Model with Causality Constraint for Mitigating Biases in Recommender Systems [20.672668625179526]
  Latent confounding bias can obscure the true causal relationship between user feedback and item exposure.<n>We propose a novel generative framework called Latent Causality Constraints for Debiasing representation learning in Recommender Systems.
  arXiv  Detail & Related papers  (2025-05-22T14:09:39Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• ROPO: Robust Preference Optimization for Large Language Models [59.10763211091664]
  We propose an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods.
  arXiv  Detail & Related papers  (2024-04-05T13:58:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.