Related papers: Specifying and Reasoning about Contextual Preferen…
We study a linear contextual optimization problem where a decision maker has access to historical data and contextual features to learn a cost prediction model aimed at minimizing decision error. We adopt the predict-then-optimize framework…
What is motivation and how does it work? Where do goals come from and how do they vary within and between species and individuals? Why do we prefer some things over others? MEDO is a theoretical framework for understanding these questions…
As large language models (LLMs) see greater use in academic and commercial settings, there is increasing interest in methods that allow language models to generate texts aligned with human preferences. In this paper, we present an initial…
The use of conceptual models to foster requirements engineering has been proposed and evaluated as beneficial for several decades. For instance, goal-oriented requirements engineering or the specification of scenarios are commonly done…
Recent advances in large pretrained models have led to their widespread integration as core components in modern software systems. The trend is expected to continue in the foreseeable future. Unlike traditional software systems governed by…
Two of the common features of business and the web are diversity and dynamism. Diversity results in users having different preferences for the quality requirements of a system. Diversity also makes possible alternative implementations for…
Given a sequence of sets, where each set has a timestamp and contains an arbitrary number of elements, temporal sets prediction aims to predict the elements in the subsequent set. Previous studies for temporal sets prediction mainly focus…
Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…
Many real-world engineering problems rely on human preferences to guide their design and optimization. We present PrefOpt, an open source package to simplify sequential optimization tasks that incorporate human preference feedback. Our…
Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…
Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human…
A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered to…
Background. Feature Model (FM) is the most important technique used to manage the variability through products in Software Product Lines (SPLs). Often, the SPLs requirements variability is by using variable use case model which is a real…
Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user…
In recent years, significant progress has been made in multi-objective reinforcement learning (RL) research, which aims to balance multiple objectives by incorporating preferences for each objective. In most existing studies, specific…
Process mining aims to comprehend and enhance business processes by analyzing event logs. Recently, object-centric process mining has gained traction by considering multiple objects interacting with each other in a process. This…
Contextuality has been identified as a potential resource responsible for the quantum advantage in several tasks. It is then necessary to develop a resource-theoretic framework for contextuality, both in its standard and generalized forms.…
In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…
Use case specifications have successfully been used for requirements description. They allow joining, in the same modeling space, the expectations of the stakeholders as well as the needs of the software engineer and analyst involved in the…
As language models (LMs) become more capable, it is increasingly important to align them with human preferences. However, the dominant paradigm for training Preference Models (PMs) for that purpose suffers from fundamental limitations, such…