Signals 4 · free daily AI digest

When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs

Paper recorded by Signals 4 on 2026-09-21 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.CL · 自然语言处理 · first seen 2026-09-22

Abstract

Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generic reconstruction, perplexity, or answer accuracy. But in explanation-critical domains, preserving only the final answer may be insufficient, since users may also inspect generated rationales to judge whether a prediction is trustworthy. We study thi

Read on arXiv →

#11 most recent of 212 cs.CL papers we have recorded · ↑ newer: MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborativ · ↓ older: Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Effic
Cite this page: When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs: the #11 most recent of 212 cs.CL papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/when-quantization-preserves-accuracy-but-not-evidence-explanation-aware-post-tra.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions