Pith. sign in

REVIEW 33 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

classification cs.CL
keywords prompttuningp-tuningtasksacrossfinetuningmodelonly
verification ladder T0 review T1 audit T2 compute T3 formal
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 to comment.

Forward citations

Cited by 33 Pith papers

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

  1. Dual Information Speech Language Models for Emotional Conversations

    cs.CL 2025-08 conditional novelty 7.0 of 10

    A dual-adapter design with equivalence replacement regularization lets frozen LLMs perceive both paralinguistic and linguistic information from speech for emotional conversation.

  2. GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models

    cs.AI 2026-06 conditional novelty 6.0 of 10

    A LoRA-tuned LLM with trie-constrained decoding improves grocery category recommendation and yields a 7.5% cart-add lift in production.

  3. Meta-cavity Quantum Electrodynamics

    physics.optics 2026-03 unverdicted novelty 6.0 of 10

    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.

  4. MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts

    cs.AI 2025-10 conditional novelty 6.0 of 10

    MHA-RAG encodes retrieved exemplars into order-invariant soft prompts via multi-head attention, claiming ~20-point effective-accuracy gains over RAG at ~10x lower inference FLOPs.

  5. Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

    cs.RO 2025-09 conditional novelty 6.0 of 10

    Editing a frozen RL policy's latent activations at inference time, using a collision world model, cuts collisions by about 90% on a curated set of hard multirotor scenarios and on real Crazyflies.

  6. Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs

    cs.AI 2025-09 conditional novelty 6.0 of 10

    CogEdit and MIND shift multimodal knowledge editing toward evaluating and enabling meta-cognitive skills: self-awareness, boundary monitoring, and noise robustness.

  7. Adversarial Topic-aware Prompt-tuning for Cross-topic Automated Essay Scoring

    cs.CL 2025-08 reject novelty 6.0 of 10

    ATOP uses shared and topic-specific soft prompts with adversarial training and pseudo-labels to improve cross-topic automated essay scoring, reporting better QWK scores than nine baselines on ASAP++.

  8. Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity

    cs.CL 2025-07 conditional novelty 6.0 of 10

    ADELL improves few-shot NER by combining dual similarity (semantic plus learned feature Jaccard) for demonstration selection with adversarial demonstration training that forces the tagger to attend to demonstrations.

  9. Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language Models

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A vision-language model fine-tuned on a new synthetic slide-animation dataset outperforms GPT-4.1 and Gemini-2.5-Pro at describing slide animations, especially on synthetic evaluation data.

  10. Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Graft merges two domain-specialized multimodal models by combining channel-wise gating, entropy-based global weighting, and an activation compatibility score to improve fusion without retraining.

  11. Test3R: Learning to Reconstruct 3D at Test Time

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Test3R improves 3D reconstruction by optimizing visual prompts at test time so that pointmaps from different image pairs are geometrically consistent.

  12. Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations

    cs.AI 2025-06 conditional novelty 6.0 of 10

    SSP adds a learned, sample-specific noise prompt to an LLM input and scores hallucination by the cosine shift in intermediate representations, outperforming output-confidence baselines on QA benchmarks.

  13. Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A federated fine-tuning method prunes 90% of attention heads, weights updates by attention importance, and selects clients by loss gap, cutting communication 1.8x and training compute 3.9x with under 2% accuracy drop.

  14. DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DA-VPT guides visual prompts with a proxy-anchor metric loss and dynamic class-to-prompt clustering, reporting consistent gains over VPT baselines across classification and segmentation.

  15. Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models

    cs.CR 2025-05 conditional novelty 6.0 of 10

    SecFPP combines hierarchical prompt decomposition with secret-sharing-based adaptive clustering to protect user prompts in federated learning while preserving personalization accuracy.

  16. PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter

    cs.CV 2025-05 conditional novelty 6.0 of 10

    PMA adapts frozen point cloud models by ordering and fusing all intermediate layer features with Mamba, achieving parameter-efficient gains on ScanObjectNN, ModelNet40, and ShapeNetPart.

  17. Can Multimodal Large Language Models Understand Spatial Relations?

    cs.CV 2025-05 conditional novelty 6.0 of 10

    SpatialMQA, a new spatial-relation benchmark, shows the top MLLM reaches 48.14% accuracy versus 98.40% for humans.

  18. Data-Efficient Adaptation of LLMs via Attention Head Reweighting

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Learning a single scalar per attention head lets LLMs adapt to few-shot text classification better than LoRA, with 200–1000x fewer trainable parameters.

  19. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

  20. AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution

    cs.CV 2025-09 conditional novelty 5.0 of 10

    Selfie images can be used to predict skin hydration and water loss with R2 up to about 0.35, using a new dataset of 336 panelists and an adapter-based vision transformer.

  21. CLAImate: AI-Enabled Climate Change Communication through Personalized and Localized Narrative Visualizations

    cs.HC 2025-07 conditional novelty 5.0 of 10

    A personalized, localized AI conversation system for climate communication shows modest factual accuracy and positive early feedback from 10 UK users.

  22. Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    GPAWP prunes low-importance graph prompts using gradient-based importance masks and retunes the remaining prompts, improving few-shot node classification over HGPrompt on ACM, DBLP, and Freebase.

  23. EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices

    cs.DC 2025-07 conditional novelty 5.0 of 10

    EdgeLoRA combines automatic adapter routing, LRU caching with a memory pool, and grouped LoRA batching to serve thousands of LoRA adapters on edge devices with up to 4x higher throughput than llama.cpp.

  24. CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge

    cs.AR 2025-06 conditional novelty 5.0 of 10

    CLONE combines generative pruning, LoRA adapters, a parameter-free Mixture-of-Experts router, and learning-based DVFS to make LLM inference on edge devices faster and more energy-efficient, claiming up to 11.92x speed...

  25. FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts

    cs.LG 2025-05 conditional novelty 5.0 of 10

    FLoE uses Fisher information to pick the transformer layers that matter and a Bayesian optimizer to set LoRA rank, cutting trainable parameters while keeping or improving accuracy.

  26. Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Quaff shows that activation outlier channels keep their spatial positions during LLM fine-tuning, and exploits this stability to cut fine-tuning memory and latency with INT8 quantization while matching or beating full...

  27. Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A closed-form concept erasure method that enforces zero alignment residual in the optimization objective and applies updates progressively across layers to better preserve generation quality.

  28. Foundation Models and Transformers for Anomaly Detection: A Survey

    cs.LG 2025-07 reject novelty 4.0 of 10

    A taxonomy and literature review of Transformer-based visual anomaly detection, compromised by fabricated citations with dummy arXiv IDs.

  29. SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models

    cs.AI 2025-07 reject novelty 4.0 of 10

    The paper proposes a multi-agent loop (instructor, follower, feedback) to auto-generate human-readable system prompts, claiming good benchmark performance and readability, but the supporting experiments are not reprod...

  30. Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A survey of context-aware machine translation with large language models, categorizing prompting, fine-tuning, and agent-based approaches.

  31. OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation

    cs.CL 2025-05 reject novelty 4.0 of 10

    OSoRA fine-tunes LLMs by updating only singular values and one output-dimension vector, using frozen singular vectors from an SVD of the pretrained weights.

  32. Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models

    cs.CL 2025-06 reject novelty 2.0 of 10

    A progressive scheduling trick that updates only the last remaining blocks in later epochs reduces parameter-update counts by about 25% with roughly unchanged GLUE and SQuAD scores.

  33. PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore

    cs.CL 2025-05 reject novelty 2.0 of 10

    PL-FGSA claims a prompt-learning TextCNN framework for fine-grained sentiment analysis, but the reported results lack baseline comparisons and few-shot validation.

Pith tools