4 papers
The Asymmetric Effects of Knowledge Distillation on Bias in Small Language Models
Plawan Kumar Rath
We show that knowledge distillation (KD) in small instruction-tuned language models has asymmetric effects on bias, and that measuring them correctly requires accounting for where…
Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
Plawan Kumar Rath
Multi-Level Intermediate Representation (MLIR) underlies modern ML compiler infrastructure (TensorFlow, JAX/StableHLO, PyTorch Inductor, IREE), yet appears only in trace amounts in…
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
Plawan Kumar Rath, Rahul Maliakkal
Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deployment, yet the impact of this c…
Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI
Plawan Kumar Rath, Rahul Maliakkal
Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We…