The paper introduces RATIO, a framework for improving quantized reasoning models by identifying overthinking tokens and applying token-specific penalties. It uses Quantization-aware Reasoning Behavior Analysis to detect problematic tokens and Token-Specific Penalty Determination to assign penalties without extra training. Experiments show RATIO outperforms existing methods, boosting accuracy by up to 9.8 points and shortening chain-of-thought length by up to 51.3%.
By Chengzhu Bao, Xianglong Yan, Tianao Zhang, Jiaqi Chen, Shaoqiu Zhang, Yulun Zhang
arXiv:2606. 25519v1 Announce Type: cross Abstract: Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token latency.
By Xinyu Lian, Walid Krichene, Beichen Huang, Masahiro Tanaka, Olatunji Ruwase, Li Zhang, Minjia Zhang
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:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.
By Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov, Pavel Vasiliev, Aleksandr Beznosikov
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
arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.
By Daeyeop Lee, Hwanjo Yu
Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count.
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.
As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...
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
The paper introduces Divergent Token Confidence (DTC), a method that estimates large language model confidence by counting tokens where two models strongly disagree during decoding. DTC uses Jensen-Shannon divergence between next-token distributions along the same reasoning trajectory and shows a near-negative correlation with answer accuracy. Experiments on multiple model families and six mathematical benchmarks demonstrate that DTC improves calibration over traditional probability-based and verbalized baselines, achieving lower expected calibration errors in both white-box and black-box settings.
By Feiyang Li, Shengjing Liu, Qi Zhan, Sijie Cheng, Weiqing Wang, Hongwen Chen, Yuxuan Yang, Wen Wang, Yile Wang, Hui Huang
arXiv:2609.26708v1 Announce Type: new
Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathema...
By Yuanteng Chen, Zhilei Liu, Peisong Wang, Yuantian Shao, Chuangyi Li, Weining Wang, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng