Pith. sign in

REVIEW 8 cited by

Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference

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 2001.07676 v3 pith:F2QLKMOR submitted 2020-01-21 cs.CL

classification cs.CL
keywords traininglanguagesupervisedexampleslargenaturalphrasessemi-supervised
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart, we show in this work that the two ideas can be combined: We introduce Pattern-Exploiting Training (PET), a semi-supervised training procedure that reformulates input examples as cloze-style phrases to help language models understand a given task. These phrases are then used to assign soft labels to a large set of unlabeled examples. Finally, standard supervised training is performed on the resulting training set. For several tasks and languages, PET outperforms supervised training and strong semi-supervised approaches in low-resource settings by a large margin.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Machine Understanding of Scientific Language

    cs.CL 2025-06 conditional novelty 7.0 of 10

    The thesis defines and evaluates tasks and datasets for automatic fact checking, cite-worthiness, exaggeration detection, and information change measurement in science communication, culminating in SPICED, a cross-med...

  2. Tiny Reward Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    TinyRM shows that 400M-parameter bidirectional masked language models, tuned with FLAN-style prompting, DoRA, and layer freezing, outperform a 70B reward model on RewardBench reasoning and come close on safety.

  3. 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.

  4. BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning

    cs.LG 2026-08 reject novelty 4.0 of 10

    A 90%-pruned few-shot Bengali model is reported to rival larger baselines on some tasks, but the reported F1 scores contradict the paper's own precision and recall values.

  5. Cyberbullying Detection via Aggression-Enhanced Prompting

    cs.CL 2025-08 reject novelty 4.0 of 10

    Adding predicted aggression labels to prompts improves LLM cyberbullying detection F1 on a single dataset, but the claim is confounded by prompt-format changes and missing statistics.

  6. MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learning

    cs.CV 2025-07 conditional novelty 4.0 of 10

    MSGCoOp improves CLIP few-shot generalization by averaging multiple learnable prompts guided by GPT-4 class descriptions and an orthogonality loss, gaining 1.10% harmonic mean over KgCoOp.

  7. Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A dynamic prompt recommendation system for skill-based security copilots combines retrieval, hierarchical skill selection, and telemetry-based ranking, reporting high usefulness in internal evaluations.

  8. Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages

    cs.CL 2025-06 conditional novelty 3.0 of 10

    Relabeling hate speech as metaphor pairs (red/green, summer/winter) in prompts raises Llama2's F1 on a 500-item Bengali subsample to 95.89, though the gain is reported without matched test-set comparisons or error bars.

Pith tools