Xu Han, Yuzhuang Xu, Wanxiang Che, Yuxuan Li, Pengzhan Li
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainly focus on improving the numerical accuracy of forward computation to eliminate performance degradation. In this paper, we show that extremely quantized LLMs suffer from systematic smoothness degradation beyond numerical precision loss. Through a smoothness proxy, we observe that such degradation becomes increasingly severe as the quantization bit-width decreases. Furthermore, based on sequence neighborhood modeling, we find that quantized models exhibit a rapid reduction of effective token candidates within the prediction neighborhood, which directly leads to a sparser decoding tree and degraded generation quality. To validate it, we introduce a simple smoothness-preserving principle in both post-training quantization and quantization-aware training, and demonstrate that preserving smoothness brings additional gains beyond numerical accuracy. The core goal of this paper is to highlight smoothness preservation as an important design consideration for future extreme quantization methods. Code is available at https://github.com/xuyuzhuang11/FINE. "When you reach the edge, hidden forces take over.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.08894")
get_code_for_paper("2605.08894")
have("2605.08894")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2605.08894.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2605.08894)
Connect an agent — have() is free.