# Length is a Curse and a Blessing for Document-level Semantics

arXiv: https://arxiv.org/abs/2310.16193 · HTML: https://mlsanity.com/paper/2310.16193/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [Whitening Sentence Representations for Better Semantics and Faster Retrieval](https://mlsanity.com/paper/2103.15316/) (2021)
- [DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings](https://mlsanity.com/paper/2204.10298/) (2022)
- [TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning](https://mlsanity.com/paper/2104.06979/) (2021)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2210.06432/) (2022)
- [On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning](https://mlsanity.com/paper/2212.09170/) (2022)

## Built on by (most cited first, 6 of 6)

- [SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval](https://mlsanity.com/paper/2401.13478/) (2024)
- [Scaling Language-Centric Omnimodal Representation Learning](https://mlsanity.com/paper/2510.11693/) (2025)
- [Pixel Sentence Representation Learning](https://mlsanity.com/paper/2402.08183/) (2024)
- [CAST: Corpus-Aware Self-similarity Enhanced Topic modelling](https://mlsanity.com/paper/2410.15136/) (2024)
- [Smart Multi-Modal Search: Contextual Sparse and Dense Embedding Integration in Adobe Express](https://mlsanity.com/paper/2408.14698/) (2024)
- [Understanding the Behaviors of Environment-aware Information Retrieval](https://mlsanity.com/paper/2606.16817/) (2026)

## Abstract (arXiv)

In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models. In this work, we question the length generalizability of CL-based models, i.e., their vulnerability towards length-induced semantic shift. We verify not only that length vulnerability is a significant yet overlooked research gap, but we can devise unsupervised CL methods solely depending on the semantic signal provided by document length. We first derive the theoretical foundations underlying length attacks, showing that elongating a document would intensify the high intra-document similarity that is already brought by CL. Moreover, we found that isotropy promised by CL is highly dependent on the length range of text exposed in training. Inspired by these findings, we introduce a simple yet universal document representation learning framework, LA(SER)3: length-agnostic self-reference for semantically robust sentence representation learning, achieving state-of-the-art unsupervised performance on the standard information retrieval benchmark.