The paper investigates where post‑training quantization (PTQ) harms large language models (LLMs) and how to best allocate a limited precision budget. By causally raising each layer to 8‑bit precision across nine open‑weight models, the authors find that quantization damage is diffuse rather than concentrated in specific task circuits or weight statistics, and that globally refining quantization granularity outperforms selectively protecting the most recoverable layers. They also observe that the residual accuracy loss is budget‑limited and that peak recovery locations correlate with architecture within families but not across families.
By Jundong Hu, Shekar Ramachandran
arXiv:2608. 06564v1 Announce Type: new Abstract: Quantization is how large language models are actually deployed, and below four bits it is known to hurt.
By Zekun Wu, Swati Dhiman, Adriano Koshiyama
arXiv:2606. 03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original.
By Evan Duan
Accuracy changes after language-model self-revision are usually interpreted as changes in reasoning. We show this can fail at the answer-extraction boundary, and test the failure causally rather than only observationally.
arXiv:2608.21019v1 Announce Type: cross
Abstract: Quantization is widely used to deploy large language models, but its effect on uncertainty behavior, such as confidence, margins, and abstention, is...
By Zhen Yang, Sizai Hou, Kaiwen Zheng, Yaofang Liu, Liang He, Yixuan Chen, Kangning Cui
We show that a quantized model that keeps its classification accuracy still changes $14$ to $46\%$ of its top-1 retrieval results, and that aggregate ranking metrics reveal only part of this damage. W...
arXiv:2609.35864v1 Announce Type: new
Abstract: SEC 10-K filings contain substantial financial information that is not consistently captured in structured datasets, creating a missing-data problem af...
By Prisha Nair, Roee Shraga
The paper introduces a data‑centric pipeline for post‑training language models on financial reasoning tasks. It mines open‑source reasoning traces, distills financial instruction data, and generates knowledge‑graph‑guided question‑answer pairs, then filters examples with lightweight classifiers and applies reinforcement learning with rule‑based verifiers. Experiments on FINESSE‑Bench show that retention‑aware adaptation—self‑distilled fine‑tuning and model merging—outperforms ordinary supervised fine‑tuning, improving accuracy by up to 3.0 points and avoiding regressions.
By Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii, Dmitry Stanishevskii, Dmitry Zmitrovich
arXiv:2607. 09999v1 Announce Type: cross Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.
By Renuka Oladri, Mohan Vamsi Varadaraju Priya, Jerry Wu
arXiv:2605. 17160v2 Announce Type: replace-cross Abstract: Model quantization is widely used to reduce memory, latency, and deployment cost, and is typically judged by whether predictive accuracy is preserved.
By Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi
arXiv:2609.27510v1 Announce Type: cross
Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and...
By Kaifeng Tan, Yudong Li, Linlin Shen
arXiv:2608.03854v4 Announce Type: replace
Abstract: Quantized large language models can run on consumer hardware, which motivates interest in on-premises processing of sensitive data. The reliability...
By Anton Rasmussen, Hong Qin