Pith. sign in

REVIEW 15 cited by

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 2308.07633 v4 pith:V5PEF6CJ submitted 2023-08-15 cs.CL cs.AI

A Survey on Model Compression for Large Language Models

classification cs.CL cs.AI
keywords llmscompressionlanguagelargemodelsurveyadvancementschallenges
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged as a key research area to address these challenges. This paper presents a survey of model compression techniques for LLMs. We cover methods like quantization, pruning, and knowledge distillation, highlighting recent advancements. We also discuss benchmarking strategies and evaluation metrics crucial for assessing compressed LLMs. This survey offers valuable insights for researchers and practitioners, aiming to enhance efficiency and real-world applicability of LLMs while laying a foundation for future advancements.

discussion (0)

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

Forward citations

Cited by 15 Pith papers

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

  1. Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

    cs.LG 2025-08 unverdicted novelty 8.0

    Derives non-asymptotic 2-norm and infinity-norm error bounds for deterministic and stochastic variants of OPTQ and Qronos PTQ algorithms.

  2. The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks

    cs.RO 2026-06 unverdicted novelty 7.0

    TISED framework reveals paradoxical effects where inference optimizations can lengthen task completion time on static tasks or raise success rates on dynamic tasks in embodied AI.

  3. From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents

    cs.CL 2026-05 unverdicted novelty 7.0

    A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.

  4. Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

    cs.CL 2025-12 unverdicted novelty 7.0

    Width pruning in Llama-3.2 models reduces parametric knowledge while enhancing instruction-following and preserving reasoning.

  5. Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment

    cs.AI 2026-07 conditional novelty 6.0

    Distilling an 8B reasoning teacher into a 0.6B student recovers most summary quality at ~50× speed, but teacher type—not scale alone—determines which capabilities transfer.

  6. The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks

    cs.RO 2026-06 unverdicted novelty 6.0

    TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.

  7. From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents

    cs.CL 2026-05 unverdicted novelty 6.0

    A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance...

  8. RUQuant: Towards Refining Uniform Quantization for Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    RUQuant uses block-wise composite orthogonal matrices from Householder reflections and Givens rotations plus a fine-tuned global reflection to achieve 99.8% full-precision accuracy at W6A6 and 97% at W4A4 for 13B LLMs...

  9. You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

    cs.CL 2025-11 conditional novelty 6.0

    TAQ estimates per-layer importance from hidden representations and output sensitivity on task calibration data to allocate mixed precision in a training-free PTQ setting, outperforming task-agnostic baselines on accur...

  10. ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

    cs.CL 2023-12 unverdicted novelty 6.0

    ASVD compresses LLMs by 10-30% and KV caches by 50% via activation-aware SVD that absorbs outliers into transformed weights and calibrates per-layer sensitivity.

  11. SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models

    cs.CL 2026-04 unverdicted novelty 5.0

    SEPTQ simplifies LLM post-training quantization to two steps via static global importance scoring and mask-guided column-wise weight updates, claiming superior results over baselines in low-bit settings.

  12. Precision or Peril: A PoC of Python Code Quality from Quantized Large Language Models

    cs.SE 2024-11 unverdicted novelty 3.0

    Smaller LLMs produce functional but limited Python code with variable quantization effects and quality/maintainability concerns that require validation before use.

  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. A Survey on the Memory Mechanism of Large Language Model based Agents

    cs.AI 2024-04 accept novelty 3.0

    A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.

  15. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.