4 papers
What the Abstention Option Measures: Refusal Loss, Sampling Churn, and Option Capture in Distilled Small Language Models
Plawan Kumar Rath
Small instruction-tuned language models reach phones, cars, and offline assistants through knowledge distillation, and whether a distilled model is fair enough to ship is often dec…
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…