Efficient Inference and Computation of Optimal Alternatives for Preference Languages Based On Lexicographic Models

• URL: http://arxiv.org/abs/2410.23913v1
• Date: Thu, 31 Oct 2024 13:19:31 GMT
• Title: Efficient Inference and Computation of Optimal Alternatives for Preference Languages Based On Lexicographic Models
• Abstract summary: We analyse preference consistency, for general preference languages based on lexicographic models. We identify a property, which we call strong compositionality, that applies for many natural kinds of preference statement. We consider different natural definitions of optimality, and their relations to each other, for general preference languages.
• Score: 3.399289369740637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We analyse preference inference, through consistency, for general preference languages based on lexicographic models. We identify a property, which we call strong compositionality, that applies for many natural kinds of preference statement, and that allows a greedy algorithm for determining consistency of a set of preference statements. We also consider different natural definitions of optimality, and their relations to each other, for general preference languages based on lexicographic models. Based on our framework, we show that testing consistency, and thus inference, is polynomial for a specific preference language LpqT, which allows strict and non-strict statements, comparisons between outcomes and between partial tuples, both ceteris paribus and strong statements, and their combination. Computing different kinds of optimal sets is also shown to be polynomial; this is backed up by our experimental results.

Related papers

• Comparing Scalar Objective Functions for Multi-Criteria Engineering Optimization [0.0]
  This paper compares four formulations for normalized bi-criteria minimization: weighted sums, achievement scalarizing functions, desirability functions, and a fuzzy-logic-based formulation.<n>Two analytically defined Pareto fronts, one convex and one concave, isolate the effect of the objective formulation from numerical behavior.<n>Results show that weighted sums are simple but structurally limited on concave fronts, while achievement, desirability, and fuzzy formulations reach interior non-supported regions through different mechanisms.
  arXiv  Detail & Related papers  (2026-06-26T18:51:16Z)
• From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language [47.600794349481966]
  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.
  arXiv  Detail & Related papers  (2026-06-24T04:51:55Z)
• Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models [61.21623682203952]
  We use linguistic binomials, such as men and women, where both word permutations are grammatically valid but exhibit distinct, cross-linguistic variations in conventionality.<n>We measure and compare the corpus-derived preferences with model-induced ordering probabilities of 6 open-weight language models.
  arXiv  Detail & Related papers  (2026-06-19T17:56:44Z)
• CM-Align: Consistency-based Multilingual Alignment for Large Language Models [84.19366314925593]
  We propose a consistency-based data method to construct high-quality multilingual preference data.<n> Specifically, our method includes two parts: consistency-guided English reference selection and cross-lingual consistency-based multilingual preference data construction.
  arXiv  Detail & Related papers  (2025-09-10T12:40:49Z)
• General Preference Modeling with Preference Representations for Aligning Language Models [51.14207112118503]
  We introduce preference representation learning, an approach that embeds responses into a latent space to capture intricate preference structures efficiently. We also propose preference score-based General Preference Optimization (GPO), which generalizes reward-based reinforcement learning from human feedback. Our method may enhance the alignment of foundation models with nuanced human values.
  arXiv  Detail & Related papers  (2024-10-03T04:22:55Z)
• Preference Alignment Improves Language Model-Based TTS [76.70693823683091]
  preference alignment algorithms adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores.
  arXiv  Detail & Related papers  (2024-09-19T01:58:19Z)
• 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)
• Improving Context-Aware Preference Modeling for Language Models [62.32080105403915]
  We consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We contribute context-conditioned preference datasets and experiments that investigate the ability of language models to evaluate context-specific preference.
  arXiv  Detail & Related papers  (2024-07-20T16:05:17Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  A common technique for aligning large language models (LLMs) relies on acquiring human preferences. We propose a new axis that is based on eliciting preferences jointly over the instruction-response pairs. We find that joint preferences over instruction and response pairs can significantly enhance the alignment of LLMs.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Obtaining Explainable Classification Models using Distributionally Robust Optimization [12.511155426574563]
  We study generalized linear models constructed using sets of feature value rules. An inherent trade-off exists between rule set sparsity and its prediction accuracy. We propose a new formulation to learn an ensemble of rule sets that simultaneously addresses these competing factors.
  arXiv  Detail & Related papers  (2023-11-03T15:45:34Z)
• Preference learning along multiple criteria: A game-theoretic perspective [97.94912276610002]
  We generalize the notion of a von Neumann winner to the multi-criteria setting by taking inspiration from Blackwell's approachability. Our framework allows for non-linear aggregation of preferences across criteria, and generalizes the linearization-based approach from multi-objective optimization. We show that the Blackwell winner of a multi-criteria problem instance can be computed as the solution to a convex optimization problem.
  arXiv  Detail & Related papers  (2021-05-05T03:23:11Z)
• An extended Knowledge Compilation Map for Conditional Preference Statements-based and Generalized Additive Utilities-based Languages [0.0]
  We study the complexity of queries which have not been addressed so far, like equivalence, and transformations. This contributes to a knowledge compilation map for languages based on conditional preference statements.
  arXiv  Detail & Related papers  (2021-02-08T10:19:40Z)
• Smart Choices and the Selection Monad [0.0]
  Describing systems in terms of choices and their resulting costs and rewards offers the promise of freeing algorithm designers and programmers from specifying how those choices should be made. We define two small languages that support decision-making abstractions: one with choices and rewards, and the other additionally with probabilities.
  arXiv  Detail & Related papers  (2020-07-17T12:13:16Z)
• Preference Modeling with Context-Dependent Salient Features [12.403492796441434]
  We consider the problem of estimating a ranking on a set of items from noisy pairwise comparisons given item features. Our key observation is that two items compared in isolation from other items may be compared based on only a salient subset of features.
  arXiv  Detail & Related papers  (2020-02-22T04:05:16Z)
• Multiplex Word Embeddings for Selectional Preference Acquisition [70.33531759861111]
  We propose a multiplex word embedding model, which can be easily extended according to various relations among words. Our model can effectively distinguish words with respect to different relations without introducing unnecessary sparseness.
  arXiv  Detail & Related papers  (2020-01-09T04:47:14Z)

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.