From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language

• URL: http://arxiv.org/abs/2607.16232v1
• Date: Wed, 24 Jun 2026 04:51:55 GMT
• Title: From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
• Abstract summary: We introduce emphweights to words, a method that takes a dataset of choice problems as input and automatically discovers a collection of domain-relevant preference dimensions.<n>These dimensions address both under-determination and opacity.<n>They can be applied to concentrate attribution on a small set of meaningful factors, and they can externalize the model's inferences in natural language so that users can inspect and edit them in real time.
• Score: 47.600794349481966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences. Compounding this problem, the opacity of these methods leaves human operators unable to inspect, contest, or correct models when they err. We introduce \emph{weights to words}, a method that takes a dataset of choice problems as input and automatically discovers a collection of domain-relevant preference dimensions, each described in natural language and paired with a vector in the model's representational space. These dimensions address both under-determination and opacity: they can be applied to concentrate attribution on a small set of meaningful factors, and they can externalize the model's inferences in natural language so that users can inspect and edit them in real time. We first qualitatively illustrate the method's versatility on four diverse domains: moral dilemmas, movies, wines, and free-form LLM responses. We then report two pre-registered human-subjects experiments, on moral dilemmas ($N=450$) and movie selection ($N=449$), that demonstrate its benefits for learning preference models: (1) regularizing a preference model toward the learned basis increases prediction accuracy on held-out choices, and (2) incorporating participants' structured edits further improves accuracy. In head-to-head comparisons, participants prefer the method's inferred preference profiles and endorse its predictions as more accurate.

Related papers

• Beyond the Binary: Capturing Diverse Preferences With Reward Regularization [15.518838657050173]
  We argue that this reliance on binary choices does not capture the broader, aggregate preferences of the target user in real-world tasks.<n>We introduce a simple yet effective method that augments existing binary preference datasets with synthetic preference judgments to estimate potential user disagreement.
  arXiv  Detail & Related papers  (2024-12-05T02:35:46Z)
• Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning [12.742158403867002]
  Reinforcement Learning from Human Feedback is a powerful paradigm for aligning foundation models to human values and preferences. Current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. We develop a class of multimodal RLHF methods to address the need for pluralistic alignment.
  arXiv  Detail & Related papers  (2024-08-19T15:18:30Z)
• Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning [6.230721646014307]
  We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inference.
  arXiv  Detail & Related papers  (2024-02-08T19:57:29Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
  We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy.<n>We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound.<n>Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
  arXiv  Detail & Related papers  (2023-12-01T00:54:02Z)
• Skill-Based Few-Shot Selection for In-Context Learning [123.26522773708683]
  Skill-KNN is a skill-based few-shot selection method for in-context learning. It does not require training or fine-tuning of any models, making it suitable for frequently expanding or changing example banks. Experimental results across five cross-domain semantic parsing datasets and six backbone models show that Skill-KNN significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2023-05-23T16:28:29Z)
• Rationalizing Predictions by Adversarial Information Calibration [65.19407304154177]
  We train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. We use an adversarial technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
  arXiv  Detail & Related papers  (2023-01-15T03:13:09Z)
• More Than Words: Towards Better Quality Interpretations of Text Classifiers [16.66535643383862]
  We show that token-based interpretability, while being a convenient first choice given the input interfaces of the ML models, is not the most effective one in all situations. We show that higher-level feature attributions offer several advantages: 1) they are more robust as measured by the randomization tests, 2) they lead to lower variability when using approximation-based methods like SHAP, and 3) they are more intelligible to humans in situations where the linguistic coherence resides at a higher level.
  arXiv  Detail & Related papers  (2021-12-23T10:18:50Z)
• To what extent do human explanations of model behavior align with actual model behavior? [91.67905128825402]
  We investigated the extent to which human-generated explanations of models' inference decisions align with how models actually make these decisions. We defined two alignment metrics that quantify how well natural language human explanations align with model sensitivity to input words. We find that a model's alignment with human explanations is not predicted by the model's accuracy on NLI.
  arXiv  Detail & Related papers  (2020-12-24T17:40:06Z)
• Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration [39.685626118667074]
  We train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. We use an adversarial-based technique to calibrate the information extracted by the two models. For natural language tasks, we propose to use a language-model-based regularizer to encourage the extraction of fluent rationales.
  arXiv  Detail & Related papers  (2020-12-16T11:54:15Z)

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.