arXiv Machine Learning August 20, 2026 By Shayan Shahrabi-Farahani (Shahid Beheshti University, Tehran, Iran), Dara Rahmati (Shahid Beheshti University, Tehran, Iran)

Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs

Read the original on arXiv Machine Learning →

The study investigates how post‑training quantization (PTQ) affects proactive interference (PI) in large language models. Using bitsandbytes, the authors compare FP16, INT8, and INT4/NF4 precision across three instruction‑tuned models and find that INT4 quantization markedly degrades accuracy under high interference, with INT8 also incurring a smaller penalty in two of the three models. The degradation is linked to increased same‑key intrusion errors and originates in the quantized transformer backbone rather than the output layer.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 2

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

arXiv:2512. 18934v2 Announce Type: replace-cross Abstract: Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency.

By Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram, Saathvik Dharmapuram, Utkarsh Sharma, Kevin Zhu

llms efficiency

arXiv Machine Learning

2d ago

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

arXiv:2608.20873v1 Announce Type: new Abstract: Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint,...

By Zifeng Liu, Zhiyong Du, Yaxin Lu, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing

llms fine-tuning efficiency

arXiv Machine Learning

Jul 14

Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts

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

llms efficiency benchmarks

arXiv AI

Jul 10

The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

arXiv:2607. 08734v1 Announce Type: new Abstract: Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity.

By Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung

llms efficiency

arXiv AI

Aug 11

Quantization Degradation in Large Language Models: A Signal-Noise Perspective

arXiv:2608. 08188v1 Announce Type: new Abstract: Post-training quantization reduces the deployment cost of large language models, yet how severely a quantized model degrades is not determined by bit-width alone.

By Chenxi Zhou, Pengfei Cao, Jinyu Ye, Bohan Yu, Haida Yu, Jiang Li, Jun Zhao, Kang Liu

llms efficiency

arXiv Machine Learning

Jun 2

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not

arXiv:2606. 00206v1 Announce Type: new Abstract: Post-training quantization (PTQ) is widely used to deploy large language models efficiently, but its effect on reasoning models is not well understood.

By Sanae Lotfi, Polina Kirichenko, Steven Li, Zechun Liu

llms efficiency benchmarks

One email a morning, machine-written

Related stories

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts

The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

Quantization Degradation in Large Language Models: A Signal-Noise Perspective

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not