Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

arXiv:2606.19744v1 Announce Type: new Abstract: Aligning language models with human preferences often requires optimising multiple behavioural objectives. A practical approach is to apply these objectives sequentially using preference optimisation methods such as Direct Preference Optimisation (DPO), but it remains unclear whether later training uniformly degrades preferences learned earlier or whether the effect depends on the relationship between objectives. We study sequential DPO across four preference settings covering distributional conflict, multi-attribute interaction, strong safety si

Source: arXiv cs.CL — read the full report at the original publisher.

This is a curated wire item. The Continuum Brief does not republish full third-party articles; this entry links to the original source.