相关论文: Discovering Context Effects from Raw Choice Data

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior.…

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide…

There is a growing body of research which has investigated relevance judgment in IR being influenced by multiple factors or dimensions. At the same time, the Order Effects in sequential decision making have been quantitatively detected and…

Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for prediction. However, the quality of uncertainty estimation…

We consider a reinforcement learning (RL) setting in which the agent interacts with a sequence of episodic MDPs. At the start of each episode the agent has access to some side-information or context that determines the dynamics of the MDP…

In networked environments, users frequently share recommendations about content, products, services, and courses of action with others. The extent to which such recommendations are successful and adopted is highly contextual, dependent on…

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs.…

This survey reviews recent developments in revealed preference theory. It discusses the testable implications of theories of choice that are germane to specific economic environments. The focus is on expected utility in risky environments;…

Knowing the effect of an intervention is critical for human decision-making, but current approaches for causal effect estimation rely on manual data collection and structuring, regardless of the causal assumptions. This increases both the…

Choice models for large-scale applications have historically relied on economic theories (e.g. utility maximisation) that establish relationships between the choices of individuals, their characteristics, and the attributes of the…

Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and…

We study the in-context learning dynamics of large language models (LLMs) using three instrumental learning tasks adapted from cognitive psychology. We find that LLMs update their beliefs in an asymmetric manner and learn more from…

A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by introducing Contextual MoralChoice, a dataset of moral dilemmas with systematic contextual…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning and prediction across different domains. Yet, their ability to infer temporal regularities from structured behavioral data remains underexplored. This paper…

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers…

As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias,…

Choice problems refer to selecting the best choices from several items, and learning users' preferences in choice problems is of great significance in understanding the decision making mechanisms and providing personalized services.…

Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on…

Serendipity plays a pivotal role in enhancing user satisfaction within recommender systems, yet its evaluation poses significant challenges due to its inherently subjective nature and conceptual ambiguity. Current algorithmic approaches…

Recommendation systems are an important units in today's e-commerce applications, such as targeted advertising, personalized marketing and information retrieval. In recent years, the importance of contextual information has motivated…