Related papers: Learning Parametric Distributions from Samples and…
Aligning large language models (LLMs) to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., a logistic Bradley-Terry link). Misspecification of this link can bias inferred rewards…
In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For example, in admissions, committees assess candidates on attributes such as test scores, GPA,…
This paper investigates simultaneous preference and metric learning from a crowd of respondents. A set of items represented by $d$-dimensional feature vectors and paired comparisons of the form ``item $i$ is preferable to item $j$'' made by…
Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…
Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…
Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these,…
Tempered stable distributions are frequently used in financial applications (e.g., for option pricing) in which the tails of stable distributions would be too heavy. Given the non-explicit form of the probability density function,…
The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a…
Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotators' different…
Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one input prompt, two responses, and a preference label. As curating…
We introduce a new approach to prediction in graphical models with latent-shift adaptation, i.e., where source and target environments differ in the distribution of an unobserved confounding latent variable. Previous work has shown that as…
Engineering design problems are often modeled as multi-objective optimization tasks in which a scalarized utility function selects an optimal design from the Pareto set. In practice, preferences are imperfectly known, so uncertainty in the…
It is commonly required to detect change points in sequences of random variables. In the most difficult setting of this problem, change detection must be performed sequentially with new observations being constantly received over time.…
User preference learning is generally a hard problem. Individual preferences are typically unknown even to users themselves, while the space of choices is infinite. Here we study user preference learning from information-theoretic…
We consider the problem of learning the preferences of a heterogeneous population by observing choices from an assortment of products, ads, or other offerings. Our observation model takes a form common in assortment planning applications:…
Recent research has attempted to associate preference optimization (PO) performance with the underlying preference datasets. In this work, our observation is that the differences between the preferred response $y^+$ and dispreferred…
Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel…
Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of…
Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…
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…