English
Related papers

Related papers: Reproduction Beyond Benchmarks: ConstBERT and ColB…

200 papers

This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Specifically, we fine-tuned BERT and XLNet, two bidirectional…

Machine Learning · Statistics 2019-09-24 Xinyi Liu , Artit Wangperawong

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on…

Computation and Language · Computer Science 2026-03-27 Danlu Chen , Ka Sing He , Jiahe Tian , Chenghao Xiao , Zhaofeng Wu , Taylor Berg-Kirkpatrick , Freda Shi

Machine learning (ML) reproducibility is often framed as a problem of incomplete artifact recording. This framing leads to systems that prioritize capturing datasets, code, configurations, and execution environments. However, in…

Human-Computer Interaction · Computer Science 2026-04-13 Zhiwei Li , Carl Kesselman

We provide a quantitative and qualitative analysis of self-repetition in the output of neural summarizers. We measure self-repetition as the number of n-grams of length four or longer that appear in multiple outputs of the same system. We…

Computation and Language · Computer Science 2022-10-18 Nikita Salkar , Thomas Trikalinos , Byron C. Wallace , Ani Nenkova

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference…

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

Computation and Language · Computer Science 2019-10-25 Alexandre Matton , Luke de Oliveira

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Computation and Language · Computer Science 2021-05-04 Jinchuan Tian , Rongzhi Gu , Helin Wang , Yuexian Zou

Recent conversational memory systems invest heavily in LLM-based structuring at ingestion time and learned retrieval policies at query time. We show that neither is necessary. SmartSearch retrieves from raw, unstructured conversation…

Machine Learning · Computer Science 2026-03-17 Jesper Derehag , Carlos Calva , Timmy Ghiurau

The PLAID (Performance-optimized Late Interaction Driver) algorithm for ColBERTv2 uses clustered term representations to retrieve and progressively prune documents for final (exact) document scoring. In this paper, we reproduce and fill in…

Information Retrieval · Computer Science 2024-04-24 Sean MacAvaney , Nicola Tonellotto

Augmenting pretrained language models with retrievers has shown promise in effectively solving common NLP problems, such as language modeling and question answering. In this paper, we evaluate the strengths and weaknesses of popular…

Computation and Language · Computer Science 2023-11-06 Parishad BehnamGhader , Santiago Miret , Siva Reddy

Multi-branch convolutional neural network architecture has raised lots of attention in speaker verification since the aggregation of multiple parallel branches can significantly improve performance. However, this design is not efficient…

Sound · Computer Science 2021-10-20 Yufeng Ma , Miao Zhao , Yiwei Ding , Yu Zheng , Min Liu , Minqiang Xu

High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategies, such as token pruning or layer sparsity, suffer from…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiaqi Shi , Yuechan Li , Xulong Zhang , Xiaoyang Qu , Jianzong Wang

We initiate a formal study of reproducibility in optimization. We define a quantitative measure of reproducibility of optimization procedures in the face of noisy or error-prone operations such as inexact or stochastic gradient computations…

Optimization and Control · Mathematics 2022-12-06 Kwangjun Ahn , Prateek Jain , Ziwei Ji , Satyen Kale , Praneeth Netrapalli , Gil I. Shamir

Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG may also lead to performance degradation due to imperfect retrieval and the model's limited ability to…

Computation and Language · Computer Science 2025-05-29 Shuyang Cao , Karthik Radhakrishnan , David Rosenberg , Steven Lu , Pengxiang Cheng , Lu Wang , Shiyue Zhang

Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters. Through…

Computation and Language · Computer Science 2026-04-02 MD Azizul Hakim

Retrieval augmented generation RAG is widely deployed to improve factual accuracy in language models yet it remains unclear whether smaller models of size 7B parameters or less can effectively utilize retrieved information. To investigate…

Computation and Language · Computer Science 2026-03-13 Sanchit Pandey

We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…

Computation and Language · Computer Science 2020-09-16 Aran Komatsuzaki

BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…

Information Retrieval · Computer Science 2021-04-20 Xiaoyang Chen , Kai Hui , Ben He , Xianpei Han , Le Sun , Zheng Ye

In this work, we introduce mxbai-edge-colbert-v0 models, at two different parameter counts: 17M and 32M. As part of our research, we conduct numerous experiments to improve retrieval and late-interaction models, which we intend to distill…

Information Retrieval · Computer Science 2025-10-17 Rikiya Takehi , Benjamin Clavié , Sean Lee , Aamir Shakir

In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Mingshu Zhao , Yi Luo , Yong Ouyang