Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback

• URL: http://arxiv.org/abs/2508.08486v1
• Date: Mon, 11 Aug 2025 21:42:33 GMT
• Title: Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback
• Authors: Parker Whitfill, Stewy Slocum,
• Abstract summary: LLMs rely on optimizing preference-based objectives, where these preferences are typically elicited as ordinal, binary choices between responses.<n>Recent work has focused on improving label quality or mitigating particular biases, but we identify a more fundamental limitation: these methods collect the wrong kind of data.<n>We show that selecting the optimal model requires recovering preferences over emphmodels (rather than just responses), which can only be identified given cardinal feedback about response quality.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Alignment techniques for LLMs rely on optimizing preference-based objectives -- where these preferences are typically elicited as ordinal, binary choices between responses. Recent work has focused on improving label quality or mitigating particular biases, but we identify a more fundamental limitation: these methods collect the wrong kind of data. We prove an impossibility result: no algorithm relying solely on ordinal comparisons can systematically recover the most preferred model. Intuitively, ordinal data lacks the information needed to resolve tradeoffs -- e.g., fixing a factual error on one prompt versus improving style on another. We show that selecting the optimal model requires recovering preferences over \emph{models} (rather than just responses), which can only be identified given cardinal feedback about response quality. To address this, we collect and publicly release a dataset of 25,000 cardinal judgments using willingness-to-pay elicitations, a well-established tool from experimental economics. Empirically, we find that incorporating cardinal feedback into preference fine-tuning allows models to prioritize high-impact improvements and outperform ordinal-only methods on downstream benchmarks, such as Arena-Hard.

Related papers

• Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains [67.71020482405343]
  We study how to design algorithms that can leverage additional information in the form of rating gap.<n>We present new algorithms that can achieve faster statistical rates than DPO in presence of accurate rating gap information.
  arXiv  Detail & Related papers  (2026-01-31T08:38:21Z)
• The Limits of Preference Data for Post-Training [27.229909368242517]
  We show that preference data fundamentally and significantly limits outcome-based optimization.<n>We formalize this impossibility using voting theory, drawing an analogy between how a model chooses to answer a query with how voters choose a candidate to elect.<n>This indicates that grounded human scoring and algorithmic innovations are necessary for extending the success of RL post-training to domains demanding human feedback.
  arXiv  Detail & Related papers  (2025-05-26T13:26:15Z)
• Causal LLM Routing: End-to-End Regret Minimization from Observational Data [3.3580884064577616]
  LLM routing aims to select the most appropriate model for each query.<n>Prior approaches typically adopt a decoupled strategy, where the metrics are first predicted and the model is then selected based on these estimates.<n>We propose a causal end-to-end framework that learns routing policies by minimizing decision-making regret from observational data.
  arXiv  Detail & Related papers  (2025-05-21T21:34:18Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We show that our approach consistently boosts DPO by a considerable margin.<n>Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Geometric-Averaged Preference Optimization for Soft Preference Labels [78.2746007085333]
  Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic.<n>In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
  arXiv  Detail & Related papers  (2024-09-10T17:54:28Z)
• An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting [53.36437745983783]
  We first construct a max-margin optimization-based model to model potentially non-monotonic preferences. We devise information amount measurement methods and question selection strategies to pinpoint the most informative alternative in each iteration. Two incremental preference elicitation-based algorithms are developed to learn potentially non-monotonic preferences.
  arXiv  Detail & Related papers  (2024-09-04T14:36:20Z)
• Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning [70.22819290458581]
  Reinforcement learning with human feedback (RLHF) is a widely adopted approach in current large language model pipelines. Our approach introduces two key innovations: (1) on-policy query to avoid OOD and imbalance issues in seed data, and (2) active learning to select the most informative data for preference queries.
  arXiv  Detail & Related papers  (2024-07-02T10:09:19Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization [16.57676001669012]
  In data-driven optimization, the sample performance of the obtained decision typically incurs an optimistic bias against the true performance.<n>Common techniques to correct this bias, such as cross-validation, require repeatedly solving additional optimization problems and are therefore expensive.<n>We develop a general bias correction approach that directly approximates the first-order bias and does not require solving any additional optimization problems.
  arXiv  Detail & Related papers  (2023-06-16T07:07:58Z)

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.