Metraipolis › archive › dc_c74df97c386d

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization — arXiv:2608.11045

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11045
License (as archived)
CC0-1.0
Archived
2026-10-19T06:14:33.097Z
SHA-256 of the archived text
fb9323c7dd2922acbc2852aeaade07b70807d3c2e41c4f3d75f4cf7286e2fd43
Stable URL of this page
https://metraipolis.com/documento/dc_c74df97c386d

How to cite

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization — arXiv:2608.11045 — arXiv (en), https://arxiv.org/abs/2608.11045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c74df97c386d (Metraipolis archive dc_c74df97c386d, sha256 fb9323c7dd2922acbc2852aeaade07b70807d3c2e41c4f3d75f4cf7286e2fd43)
BibTeX
@misc{dcc74df97c386d,
  title = {ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization — arXiv:2608.11045},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11045},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c74df97c386d; sha256 fb9323c7dd2922acbc2852aeaade07b70807d3c2e41c4f3d75f4cf7286e2fd43},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting from a pretrained LLM, ReRound trains a conditional diffusion model to produce continuous reconstructions of low-bit weights for the LLM. These reconstructed weights act as a guidance signal to disambiguate the rounding direction of weights located close to interval midpoints. To integrate this reconstruction-guided rounding with conventional RTN, ReRound introduces a tolerance metric measuring how far the quantized weight (not the final quantized integer) is away from the midpoint: quantized weights within a tolerance region around midpoints are quantized using diffusion-based reconstructions, whereas weights closer to quantization boundaries are quantized with RTN. By sweeping the tolerance parameter, ReRound generates multiple candidate quantized integer weight matrices and selects the de-quantized weight matrix candidate whose leading singular values most closely match those of the original full-precision weights. This selected candidate determines the tolerance parameter ReRound uses. ReRound is particularly effective for smaller LLMs. Across a range of such models, it consistently outperforms standard RTN for 3-bit and 4-bit weight quantization. ReRound achieves superior accuracy compared to an extensive set of calibration-free methods, remains competitive with calibration-dependent approaches, and operates entirely offline, introducing no additional overhead during low-bit inference. The ReRound strategy represents a new approach for low-bit quantization. The method applies to AI models beyond LLMs. This paper focuses on its applications to small LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CL).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.11045 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T06:08:50.373Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).