mlsanityData to 14 Oct 2026

Analyzing Text Representations by Measuring Task Alignment

arXiv 2305.19747 ↗First posted 31 May 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Textual representations based on pre-trained language models are key, especially in few-shot learning scenarios. What makes a representation good for text classification? Is it due to the geometric properties of the space or because it is well aligned with the task? We hypothesize the second claim. To test it, we develop a task alignment score based on hierarchical clustering that measures alignment at different levels of granularity. Our experiments on text classification validate our hypothesis by showing that task alignment can explain the classification performance of a given representation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

22 of 45 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  4. 2016Bag of Tricks for Efficient Text Classificationcited by 876
  5. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  6. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  7. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 457
  8. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 438
  9. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  10. 2018SentEval: An Evaluation Toolkit for Universal Sentence Representationscited by 294
  11. 2018Targeted Syntactic Evaluation of Language Modelscited by 242
  12. 2019Visualizing and Measuring the Geometry of BERTcited by 216
10 more
  1. 2016Ex Machina: Personal Attacks Seen at Scalecited by 210
  2. 2019Emerging Cross-lingual Structure in Pretrained Language Modelscited by 181
  3. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  4. 2020A Survey of Active Learning for Text Classification using Deep Neural Networkscited by 50
  5. 2021DirectProbe: Studying Representations without Classifierscited by 25
  6. 2019Probing Multilingual Sentence Representations With X-Probecited by 13
  7. 2022Cluster & Tune: Boost Cold Start Performance in Text Classificationcited by 13
  8. 2021Comparing Text Representations: A Theory-Driven Approachcited by 5
  9. 2016The Benefits of Word Embeddings Features for Active Learning in Clinical Information Extractioncited by 3
  10. 2019Investigating the Effectiveness of Representations Based on Word-Embeddings in Active Learning for Labelling Text Datasetscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddingscited by 2
  2. 2025Domain Pre-training Impact on Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Singular Vectors of Attention Heads Align with Features
  2. 2023Text-To-KG Alignment: Comparing Current Methods on Classification Tasks
  3. 2024Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance
  4. 2023Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
  5. 2020Aligning the Pretraining and Finetuning Objectives of Language Models
  6. 2026Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
  7. 2026Representation Alignment Rests on Linear Structure
  8. 2024Recurrent Alignment with Hard Attention for Hierarchical Text Rating