arXiv AI
Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 14
Reliability Scaling Laws for Quantized Large Language Models
arXiv:2607. 10855v1 Announce Type: new Abstract: Quantization is a powerful strategy to build capable and resource-efficient large language models (LLMs) by reducing the bitwidth of the parameters.
arXiv AI
Oct 19
Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
The paper introduces Truth AnChoring (TAC), a lightweight post‑hoc calibration method that transforms raw uncertainty estimation scores into truth‑aligned correctness probabilities for large language models. It identifies that many existing UE metrics fail because they are derived from model behavior rather than factual correctness, leading to unstable performance across models and datasets. TAC improves calibration even with noisy, few‑shot supervision, offering a practical protocol for more reliable uncertainty estimation.
arXiv AI
Jun 2
Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
arXiv:2606. 01850v1 Announce Type: new Abstract: Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation.
arXiv Computation and Language
Sep 22
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
arXiv:2604.08974v2 Announce Type: replace Abstract: Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection an...
Hugging Face Trending Papers
Jun 22
The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models
Recent advancements in Large Language Models (LLMs) have enabled sophisticated reasoning and content generation, yet their inherent stochasticity poses significant challenges for ensuring predictive credibility. While traditional uncertainty taxonomy paradigms, such as the dichotomy of aleatoric and epistemic uncertainties, provide conceptual foundations, they often fail to capture the multi-component and multi-stage nature of LLM generation and struggle to evaluate the effectiveness of various Uncertainty Quantification (UQ) methods.
arXiv AI
Oct 9
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
The paper examines weight-only post‑training quantization (PTQ) and finds that minimizing reconstruction loss does not always improve model performance, sometimes even harming it on calibration data. It shows that weights with low reconstruction loss on one distribution can perform worse when activation distributions shift. To address this, the authors introduce Distributionally Robust Quantization (DRQ), a refinement step that minimizes worst‑case reconstruction loss over a constrained set of activation distributions while keeping the quantization grid unchanged. Experiments demonstrate that DRQ improves models quantized by several PTQ methods across dense and mixture‑of‑experts large language models, offering better downstream performance without extra inference cost.