# An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Source: [An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift](<https://www.sota2.com/research/paper/69647fdb53fdd5c3617445c8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-15T06:00:01.998Z

Authors: Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras

Published: 2026-01-09T15:56:55.000Z

## Abstract

Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades performance and reduces helpfulness when evaluated outside the training domain. However, the extent to which adaptation strategies mitigate this domain shift remains unexplored. We address this challenge by conducting a comprehensive and systematic study of alignment generalization under domain shift. We compare five popular alignment objectives and various adaptation strategies from source to target, including target-domain supervised fine-tuning and pseudo-labeling, across summarization and question-answering helpfulness tasks. Our findings reveal systematic differences in generalization across alignment objectives under domain shift. We show that adaptation strategies based on pseudo-labeling can substantially reduce domain-shift degradation

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.05882>)

[PDF](<https://arxiv.org/pdf/2601.05882.pdf>)

[Implementation](<https://github.com/ckarouzos/prefadap>)
