Papers with pooling strategies
Mind Your Special Tokens! On the Importance of Dedicated Sequence-End Tokens in Vision-Language Embedding Models (2026.eacl-short)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) are highly sensitive to end-of-input artifacts in fine-tuning and inference data, e.g., whether input sequences end with punctuation or newline characters. |
| Approach: | They propose to convert generative LVLMs into vision-language encoders via contrastive learning objectives and use supervised contrastive objectives to train them. |
| Outcome: | The proposed approach improves visual and text representations and improves retrieval and (semantic) similarity tasks. |
From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems (2025.acl-srw)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a key framework in natural language processing . however, the effectiveness of RAG is often hindered by coreferential complexity in retrieved documents . |
| Approach: | They investigate how entity coreference affects document retrieval and generative performance in RAG-based systems. |
| Outcome: | The proposed model improves QA performance and retrieval relevance and contextual understanding. |
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (P18-1)
Copied to clipboard
Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, Lawrence Carin
| Challenge: | Existing deep learning architectures to model compositionality in text sequences require a large number of parameters and expensive computations. |
| Approach: | They propose two additional pooling strategies over word embeddings for improved interpretability and hierarchical pooling for spatial (n-gram) information within text sequences. |
| Outcome: | The proposed pooling strategies improve interpretability and preserve spatial (n-gram) information within text sequences. |
Don’t be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks (2024.findings-naacl)
Copied to clipboard
| Challenge: | Offensive language detection is important for filtering out abusive expressions, authors argue . authors propose user-intended adversarial attacks that insert special symbols or leverage distinctive features of the Korean language. |
| Approach: | They propose user-intended adversarial attacks that insert special symbols or leverage the distinctive features of the Korean language. |
| Outcome: | The proposed models are more robust to performance degradation even when the attack rate is increased, compared to models trained on noisy texts. |
On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification (2020.lrec-1)
Copied to clipboard
| Challenge: | Language identification (LID) from speech is commonly tackled using similar approaches to those employed for speaker verification/recognition. |
| Approach: | They propose to combine local descriptors and global descriptores into a single global description that can be used for downstream classification tasks. |
| Outcome: | The proposed methods outperform well-known benchmark systems and previously results based on attention only. |
Less Mature is More Adaptable for Sentence-level Language Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies fine-tune encoders or contrastive learning approaches to learn sentence representations. |
| Approach: | They propose to use sentence-level models to study how sentence representations influence downstream task performance. |
| Outcome: | The proposed models outperform token-level models in terms of time and data efficiency. |
Enhancing Lexicon-Based Text Embeddings with Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. |
| Approach: | They introduce the first lexicon-based embeddings that consolidates the vocabulary space through token embeddation clustering to handle the issue of token redundancy in LLM vocabularies. |
| Outcome: | The proposed model outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB) it also supports efficient dimension pruning without any specialized objectives like Matryoshka Representation Learning. |
Investigating Multi-layer Representations for Dense Passage Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Dense retrieval models adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model contain different kinds of linguistic knowledge and behave differently during fine-tuning. |
| Approach: | They propose to utilize representations from multiple encoder layers to make up the representation of a document, which they denote Multi-layer Representations (MLR). |
| Outcome: | The proposed model outperforms dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting and with other advanced training techniques. |
Sparse Autoencoder Features for Classifications and Transferability (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) provide potential for uncovering structured, human-interpretable representations in Large Language Models (LLMs). |
| Approach: | They analyze SAEs for interpretable feature extraction from Large Language Models in safety-critical classification tasks. |
| Outcome: | The proposed framework outperforms hidden-state and BoW models while demonstrating cross-lingual toxicity detection and visual classification tasks. |
Beyond Single Representations: Multi-Model Embedding Fusion for Stable Text Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on embedding fusion have not evaluated the effectiveness of individual layers or the impact of combining embeddables from multiple models. |
| Approach: | They propose to combine embeddings from multiple models to improve performance across NLP tasks. |
| Outcome: | The proposed method improves performance on low-resource datasets and reduces the impact of any single model as the number of integrated models increases. |