arXiv research

We propose a decomposition technique to reduce user cognitive load in constructive preference elicitation.

This paper develops a new method for eliciting more flexible metrics, improving fairness and applicability.

Study creates web interface to elicit user-preferred metrics.

In this paper we propose an approach to preference elicitation that is suitable to large configuration spaces beyond the reach of existing state-of-the-art approaches. Our setwise max-margin method can be viewed as a generalization of max-margin learning to sets, and can produce a set of "diverse" items that can be use…

Proposes a method to select fair performance metrics through metric elicitation.

Cost-effective framework for eliciting and aggregating preferences.

A framework for eliciting utility functions from investor preferences.

Gradient optimization improves preference elicitation for large item spaces.

This paper improves decision support in multi-objective planning by better eliciting user preferences.

This thesis formalizes metric selection for machine learning applications.

Formulates a Dueling Bandits problem for eliciting Kemeny rankings.

We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optio…

Study shows LLM-advisors match human performance in eliciting preferences but struggle with conflicting needs and trust.

Framework uses IRL and RL to elicit and optimize risk preferences robustly to noise.

Paper develops a robust preference model for multi-attribute choices.

Platform uses queries to elicit investor preferences for portfolio trades, improving allocation efficiency.

Elicit performance metrics from classifier comparisons.

Bayesian method helps decision-makers find preferred solutions in multi-objective optimization.

Constructs new elicitable risk measures with multiplicative scoring functions.

GBS uses machine learning to design products based on consumer preferences.

Develops a statistical framework to measure uncertainty in model rankings based on human preferences.

New algorithm speeds up user preference learning in conversational contexts.

Study on identifying most preferred policy in bandits with vector-valued rewards.

Motivated by an application of eliciting users' preferences, we investigate the problem of learning hemimetrics, i.e., pairwise distances among a set of $n$ items that satisfy triangle inequalities and non-negativity constraints. In our application, the (asymmetric) distances quantify private costs a user incurs when s…

Duel-Evolve uses LLM self-preferences for test-time optimization of discrete outputs.

Paper analyzes finite-time guarantees for preference-based RL.

This study measures price risk aversion using indirect utility functions in a lab experiment.

Extends Mallows model to handle item indifference in rankings.

Develops methods for eliciting multiple, continuously valued treatment policies using causal inverse classification.

The paper analyzes elicitability of return risk measures and their scoring functions.

New method estimates composite outcomes for precision medicine.

Response time improves alignment with diverse human preferences.

The paper enhances preference learning by incorporating response time data.

The paper tackles PAC ranking with subset-wise feedback, achieving optimal sample complexity.

LLMs can be influenced by unseen dataset subtexts, revealing new ways to select data subsets.

FedConPE improves conversational recommender systems efficiency and privacy.

ELECTRE Tree infers ELECTRE Tri-B parameters using a machine learning approach.

New algorithm learns human preferences from few comparisons efficiently.

Sharpe et al. proposed the idea of having an expected utility maximizer choose a probability distribution for future wealth as an input to her investment problem instead of a utility function. They developed a computer program, called The Distribution Builder, as one way to elicit such a distribution. In a single-perio…

A property, or statistical functional, is said to be elicitable if it minimizes expected loss for some loss function. The study of which properties are elicitable sheds light on the capabilities and limitations of point estimation and empirical risk minimization. While recent work asks which properties are elicitable, …

Crowdsourced wisdom improves causal learning.

We discuss equivalent axiomatic characterizations of distortion risk measures, and give a novel and concise proof of the characterization of elicitable distortion risk measures. Elicitability has recently been discussed as a desirable criterion for risk measures, motivated by statistical considerations of forecasting. …

This paper tackles sample elicitation for learning systems, introducing a method to incentivize truthful samples.

Robustifies elicitable functionals to handle small distribution misspecifications.

Study generalizes property elicitation to imprecise probabilities.

A statistical functional, such as the mean or the median, is called elicitable if there is a scoring function or loss function such that the correct forecast of the functional is the unique minimizer of the expected score. Such scoring functions are called strictly consistent for the functional. The elicitability of a …

Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcem…

Active Inverse Reward Design improves AI agent training by querying users for reward function preferences.