Pith. sign in

REVIEW 14 cited by

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.08659 v4 pith:URQTB6NQ submitted 2023-10-12 cs.CL cs.AIcs.LG

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

classification cs.CL cs.AIcs.LG
keywords quantizationfine-tuninglanguageloraloftqtasksdownstreaminitialization
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on a pre-trained model. In such cases it is common to observe a consistent gap in the performance on downstream tasks between full fine-tuning and quantization plus LoRA fine-tuning approach. In response, we propose LoftQ (LoRA-Fine-Tuning-aware Quantization), a novel quantization framework that simultaneously quantizes an LLM and finds a proper low-rank initialization for LoRA fine-tuning. Such an initialization alleviates the discrepancy between the quantized and full-precision model and significantly improves generalization in downstream tasks. We evaluate our method on natural language understanding, question answering, summarization, and natural language generation tasks. Experiments show that our method is highly effective and outperforms existing quantization methods, especially in the challenging 2-bit and 2/4-bit mixed precision regimes. The code is available on https://github.com/yxli2123/LoftQ.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation

    cs.LG 2026-05 unverdicted novelty 8.0

    GPTQ-intrinsic LoRA augments GPTQ with intrinsic low-rank compensation via Hessian modification to achieve layer-wise reconstruction bounds that match information-theoretic lower bounds under structural assumptions.

  2. Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions

    cs.AI 2026-04 unverdicted novelty 7.0

    Intent2Tx shows that LLMs often generate syntactically valid but functionally incorrect Ethereum transactions, especially on multi-step and out-of-distribution intents, despite gains from scaling and retrieval augmentation.

  3. Dive Into the Implicit Biases of Low-rank Vision-language Alignment

    cs.CV 2026-07 conditional novelty 6.0

    Low-rank LLM adaptation during vision-language alignment outperforms full fine-tuning by preserving per-token visual structure and favoring flat, noise-robust subspaces.

  4. SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving

    cs.AR 2026-06 unverdicted novelty 6.0

    SPEAR places input-dependent error compensators at CKA-selected layers and fuses them into low-bit GEMMs to recover 56-75% of the W4-to-FP16 perplexity gap with <1% memory overhead and near-baseline latency.

  5. ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

    cs.LG 2026-05 unverdicted novelty 6.0

    ProjQ constrains post-training quantization noise to a low-rank manifold through orthogonal subspace projection, enabling better compensation by LoRA adapters and preserving greater model plasticity than standard PTQ.

  6. GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning

    cs.LG 2026-05 unverdicted novelty 6.0

    GPart is a PEFT technique that achieves end-to-end isometry by using a single random isometric partition matrix to map a low-dimensional trainable vector into full model weights without low-rank structure.

  7. Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models

    cs.CL 2025-08 conditional novelty 6.0

    A progressive training scheme with binary-aware initialization and dual-scaling allows pre-trained LLMs to be converted to high-performance 1-bit models without training from scratch.

  8. LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

    cs.LG 2025-06 unverdicted novelty 6.0

    LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.

  9. Efficient Reasoning on the Edge

    cs.LG 2026-03 accept novelty 5.5

    LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.

  10. HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices

    cs.LG 2026-05 unverdicted novelty 5.0

    HCInfer recovers up to 5.2% accuracy over compressed LLMs and delivers 10.4x speedup versus full-precision models by offloading compensation parameters to CPU with async execution on resource-limited hardware.

  11. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

    cs.LG 2024-03 accept novelty 4.0

    A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.

  12. ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook

    eess.SP 2026-04 unverdicted novelty 3.0

    ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.

  13. A Survey on Efficient Inference for Large Language Models

    cs.CL 2024-04 accept novelty 3.0

    The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.

  14. Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

    cs.CR 2024-09 unverdicted novelty 2.0

    Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.