Pith. sign in

REVIEW 20 cited by

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

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 2110.07602 v3 pith:STTKRJFK submitted 2021-10-14 cs.CL

P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

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

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not perform well for normal-sized pretrained models. We also find that existing methods of prompt tuning cannot handle hard sequence labeling tasks, indicating a lack of universality. We present a novel empirical finding that properly optimized prompt tuning can be universally effective across a wide range of model scales and NLU tasks. It matches the performance of finetuning while having only 0.1%-3% tuned parameters. Our method P-Tuning v2 is an implementation of Deep Prompt Tuning \cite{li2021prefix,qin2021learning} optimized and adapted for NLU. Given the universality and simplicity of P-Tuning v2, we believe it can serve as an alternative to finetuning and a strong baseline for future research.Our code and data are released at https://github.com/THUDM/P-tuning-v2.

discussion (0)

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

Forward citations

Cited by 20 Pith papers

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

  1. EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

    cs.CL 2023-09 unverdicted novelty 7.0

    EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.

  2. LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

    cs.CV 2023-03 conditional novelty 7.0

    LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.

  3. SoftSkill: Behavioral Compression for Contextual Adaptation

    cs.AI 2026-06 unverdicted novelty 6.0

    SoftSkill compresses agent skills into length-32 continuous prefixes via next-token training of soft deltas, yielding 5.2-12.5 point gains over SkillOpt on SearchQA and LiveMath while using far fewer tokens.

  4. Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning

    cs.CL 2026-06 unverdicted novelty 6.0

    SDBN introduces adversarial training to PEFT via two variants using character-level edits and LLM-generated perturbations, claiming improved robustness and generalization on NLP benchmarks in low-resource noisy settings.

  5. Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

    cs.LG 2026-06 unverdicted novelty 6.0

    Empirical benchmarks show distribution similarity between adaptation and pretraining data increases practical privacy leakage in DP-adapted LLMs at fixed theoretical guarantees, with LoRA providing strongest protectio...

  6. Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

    cs.CR 2026-06 unverdicted novelty 6.0

    Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.

  7. Latent Diffusion Pretraining for Crystal Property Prediction

    cs.LG 2026-05 unverdicted novelty 6.0

    CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.

  8. TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering

    q-bio.QM 2026-05 unverdicted novelty 6.0

    TadA-Bench supplies a chronological million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds that evaluates models on future-round variant ranking given only earlier data.

  9. PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts

    cs.CL 2026-05 unverdicted novelty 6.0

    PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.

  10. TLoRA: Task-aware Low Rank Adaptation of Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer ...

  11. Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs

    cs.CL 2026-04 unverdicted novelty 6.0

    Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.

  12. Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise

    cs.CV 2026-04 unverdicted novelty 6.0

    VisPrompt improves prompt learning robustness under label noise by injecting instance-level visual semantics via attention and adaptive modulation while freezing the VLM backbone.

  13. Meta-cavity Quantum Electrodynamics

    physics.optics 2026-03 unverdicted novelty 6.0

    Quantum dots in ultrathin geometric-phase metacavities emit triggered single photons that are simultaneously Purcell-enhanced and wavefront-shaped into vortices, holograms, or spin-locked beams.

  14. PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

    cs.CL 2025-06 unverdicted novelty 6.0

    PrefixMemory-Tuning decouples the prefix from attention to overcome performance limits of traditional prefix-tuning and reaches competitive results with modern PEFT methods on LLM adaptation benchmarks.

  15. Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

    cs.CL 2023-05 conditional novelty 6.0

    UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.

  16. FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

    cs.LG 2026-04 unverdicted novelty 5.0

    FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.

  17. No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation

    cs.CV 2026-06 unverdicted novelty 4.0

    Observability-constrained test-time prompt tuning for LiDAR semantic segmentation reweights spatial supervision using per-location reliability estimates from beam terminations and neighborhood support, with prompt ada...

  18. Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization

    cs.LG 2026-05 unverdicted novelty 4.0

    FoLoRA applies generalized Rayleigh-quotient optimization to LoRA updates so that directions are gated by downstream utility divided by a pretraining-proxy forgetting penalty.

  19. 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.

  20. The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge

    cs.LG 2026-04 unverdicted novelty 2.0

    A competition entry achieved efficient fine-tuning of LLaMa2 70B on one GPU in 24 hours with competitive QA benchmark performance.