Search papers, labs, and topics across Lattice.
This study re-evaluates the role of supervised fine-tuning (SFT) by framing online data selection as an implicit alignment mechanism that influences model behavior. By comparing various online selectors鈥攔andom, loss-based, quality-based, and diversity-based鈥攖he authors demonstrate that even without explicit preference optimization, the choice of training data can significantly alter behavioral outcomes such as verbosity and compliance. The findings reveal that high-scoring data can systematically favor specific response styles, highlighting the importance of data selection in shaping model alignment and safety.
Online data selection can shift model behavior as much as explicit preference optimization, revealing a hidden layer of alignment influence.
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences. We study online data selection as an implicit alignment mechanism. Given the same base model, optimizer, and selected-token budget, we compare random, loss-based, quality-based, and diversity-based online selectors and measure the behavioral drift they induce without any preference optimization. The proposed evaluation tracks helpfulness, refusal rate, verbosity, truthfulness, sycophancy, calibration, and jailbreak robustness, together with diagnostics for which behavioral modes are over-represented in the selected data. We formalize online selection as a reweighted SFT objective whose weights define an implicit preference over response styles and safety postures, so that an online scorer plays the role usually assigned to a reward model. This view predicts that high-scoring data can systematically favor longer, more assertive, more compliant, or more refusal-prone behaviors depending on how the online score is defined. Empirically, selectors that are statistically indistinguishable in task accuracy diverge sharply in refusal rate, verbosity, and sycophancy, and we show that the direction of the shift is predictable from the attribute mixture of the selected data. We introduce Alignment Drift Auditing (ADA), a controlled protocol for quantifying selection-induced behavioral movement, and Alignment-Aware Selection (AAS), a diagnostic online selector that retains data efficiency while constraining drift along safety and style axes.
