Empirical Evaluation of DPZero for Private Fine-Tuning of RoBERTa-large on SST-2

Adaptive Hyperparameter Tuning for Differentially Private Linear Regression: A Practical Survey and Empirical Study

When Tuning Isn't Enough: Limits of Inference-Time Controls and Collaboration in Small Local LLMs

We study the limits of inference-time parameter tuning and multi-model collaboration for locally-deployed small LLMs (3B-14B) in a small on-premises deployment using quantized models on a 16 GB GPU. Although these techniques are widely used in local, compliance-constrained deployments to improve model quality without r...

Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference

An empirical error-propagation analysis is developed and finds that 22 layers of accumulated body error do not distinguish flipping from non-flipping steps; the outcome depends primarily on the top-two logit margin at the LM head relative to the directional perturbation between the top-two candidates.

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

Debias-SparseGPT is introduced, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs that consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy.

Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores

We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through selection and its audit trace by post-processing. End-to-end privacy holds only when selector inputs are public or independent, previous priva...

Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning

This is the first study to target worst-case demographic personas with LoRA fine-tuning for cross-cultural bias mitigation, and country-level decomposition reveals that fine-tuning redistributes rather than removes bias.